© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3866
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to searching for, finding and liking things

    oai_token-act-pair · gemini-2.0-flash

    expectations and searching

    np_max-act · gemini-2.0-flash

    say "space" words

    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_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.89
    OGND
    -0.73
    tagHelperRunner
    -0.70
    fjspx
    -0.68
    derry
    -0.68
    Datuak
    -0.67
     Monfieur
    -0.67
    ConstraintMaker
    -0.66
    principalColumn
    -0.66
    OrBuilder
    -0.66
    POSITIVE LOGITS
    </i>
    0.47
     ra
    0.45
     en
    0.44
     Car
    0.42
     par
    0.42
    Etimología
    0.42
     already
    0.42
     Richard
    0.40
     Ra
    0.40
    —
    0.39
    Activations Density 1.264%

    No Known Activations