© 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. 15068
    Prev
    Next
    INDEX
    Explanations

    articles, prepositions and words indicating specific limits or conditions

    oai_token-act-pair · gemini-2.0-flash

    specificity in descriptions

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

    specific

    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
    UrlResolution
    -0.74
     ModelExpression
    -0.74
    IsContent
    -0.72
     فريبيس
    -0.68
     kaynağından
    -0.66
     بيها
    -0.62
     unknownFields
    -0.59
    ]")]
    -0.57
     &___
    -0.57
    ControllerAdvice
    -0.57
    POSITIVE LOGITS
     particular
    2.45
     certain
    2.25
     specific
    2.09
    particular
    2.06
    certain
    1.91
     Particular
    1.89
     PARTICULAR
    1.84
     Certain
    1.78
    Particular
    1.78
    Specific
    1.73
    Activations Density 3.683%

    No Known Activations