© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10936
    Prev
    Next
    INDEX
    Explanations

    quantifiers that make comparisons

    oai_token-act-pair · gemini-2.0-flash

    many

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    UrlResolution
    -0.55
    RegistryLite
    -0.54
    &)
    -0.54
    pushFollow
    -0.51
    :✨
    -0.51
    DotNetBar
    -0.51
    ')));
    -0.49
    tvguidetime
    -0.48
     relâche
    -0.46
    stateProvider
    -0.45
    POSITIVE LOGITS
     many
    3.02
    many
    2.59
    Many
    2.39
     Many
    2.36
     muchos
    2.27
     MANY
    2.14
     muitos
    2.13
     muchas
    2.06
     molti
    1.97
    MANY
    1.95
    Activations Density 6.692%

    No Known Activations