© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15714
    Prev
    Next
    INDEX
    Explanations

    content surrounded by quote marks

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     
    -0.61
    )*/
    -0.56
     */}
    -0.55
    );*/
    -0.54
    ?」
    -0.53
    }}}$
    -0.53
     ་་
    -0.53
    -0.53
     ***/
    -0.52
    });*/
    -0.52
    POSITIVE LOGITS
     We
    0.60
     It
    0.54
     But
    0.54
     Our
    0.50
     You
    0.50
     He
    0.48
     Just
    0.48
     As
    0.47
     At
    0.47
     And
    0.47
    Activations Density 11.226%

    No Known Activations