© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1940
    Prev
    Next
    INDEX
    Explanations

    the word "outside" or its variants, and words related to opposition or dependence

    oai_token-act-pair · gemini-2.0-flash

    outside

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     outside
    -2.44
    outside
    -2.19
    Outside
    -2.14
     Outside
    -2.13
     OUTSIDE
    -1.90
    OUTSIDE
    -1.63
     buiten
    -1.46
     utanför
    -1.44
     exterior
    -1.36
     external
    -1.29
    POSITIVE LOGITS
    +#+#
    0.72
     oprot
    0.70
    #+#
    0.59
    vertx
    0.58
    Werde
    0.58
    weth
    0.57
    Artículos
    0.56
     initWithFrame
    0.56
    Forth
    0.55
     Cress
    0.54
    Activations Density 4.335%

    No Known Activations