© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14351
    Prev
    Next
    INDEX
    Explanations

    intensifiers such as "even," and "more," sometimes in combination with verbs concerning outcomes or conditions.

    oai_token-act-pair · gemini-2.0-flash

    comparisons

    np_max-act-logits · gemini-2.0-flash

    say "comparative/superlative"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.86
    )))));
    -0.59
    antia
    -0.58
    endphp
    -0.58
    iforn
    -0.58
    ducers
    -0.57
    ]]]
    -0.57
    fortawesome
    -0.56
     שוליים
    -0.54
     OMITBAD
    -0.54
    POSITIVE LOGITS
     Dead
    0.57
    SharedCtor
    0.51
    mappedBy
    0.51
    исленность
    0.51
     dead
    0.50
    RegressionTest
    0.49
    Dead
    0.48
    NullException
    0.47
    Personensuche
    0.46
    Patience
    0.45
    Activations Density 2.328%

    No Known Activations