© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7916
    Prev
    Next
    INDEX
    Explanations

    HTML table code

    oai_token-act-pair · gemini-2.0-flash

    structured HTML elements or tags

    np_token-act-pair-logits · gpt-4o-mini

    HTML tags

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    }))
    -0.56
    }));
    -0.54
    HttpPut
    -0.52
    定
    -0.51
    NewRow
    -0.51
    <bos>
    -0.50
     pip
    -0.50
     fixed
    -0.49
    thinkable
    -0.49
    textarea
    -0.49
    POSITIVE LOGITS
     يتيمه
    0.86
    醐
    0.81
    ScopeManager
    0.79
     Theſe
    0.69
     itſelf
    0.67
    KURZBESCHREIBUNG
    0.66
     مواليد
    0.66
    帖最后由
    0.66
    RectangleBorder
    0.63
     iNdEx
    0.61
    Activations Density 0.589%

    No Known Activations