© 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. 9866
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic places and locations, especially within a nested structure of "X in Y (in Z)"

    oai_token-act-pair · gemini-2.0-flash

    structured data labels or terms in text

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

    Locations

    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
    elemField
    -0.62
    migrationBuilder
    -0.60
    transQ
    -0.59
    Slf
    -0.59
    PyExc
    -0.58
     ویکی‌پدیا
    -0.58
    UnknownFieldSet
    -0.57
    ]--;
    -0.53
    EndInit
    -0.52
    NSError
    -0.52
    POSITIVE LOGITS
    titleMargin
    0.47
    tinyos
    0.47
     отвечает
    0.45
    ituary
    0.45
    khó
    0.44
    ροφο
    0.44
    ViewStyle
    0.44
     odpowiada
    0.44
    alnız
    0.43
    ۪
    0.42
    Activations Density 0.765%

    No Known Activations