© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6560
    Prev
    Next
    INDEX
    Explanations

    the word "and" (possibly within a certain window of other words).

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     entanto
    -0.44
    \{\\
    -0.44
     же
    -0.43
    _));
    -0.42
    bewerken
    -0.40
    ))));
    -0.40
     zaś
    -0.39
     והוא
    -0.39
    %";
    -0.39
    });*/
    -0.38
    POSITIVE LOGITS
    Tikang
    0.77
    Geplaatst
    0.74
     resourceCulture
    0.71
    XmlAccessType
    0.70
    URLException
    0.70
     الاطلاع
    0.69
    AccessorTable
    0.67
     مرئيه
    0.65
    Kariera
    0.64
    ViewFeatures
    0.63
    Activations Density 0.656%

    No Known Activations