© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13629
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated characters, like "pe", "IE", and "U]".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    tagHelperRunner
    -0.93
    rungsseite
    -0.81
    ViewFeatures
    -0.75
    تقاوى
    -0.73
     CURLOPT
    -0.73
     resourceCulture
    -0.68
     समीक्षाओं
    -0.66
    cyklopedia
    -0.62
     bağlantılar
    -0.60
    RTEE
    -0.59
    POSITIVE LOGITS
    specially
    0.53
    very
    0.50
    scape
    0.47
     tremp
    0.47
    ivamente
    0.46
    crí
    0.44
    setCharacter
    0.44
    ErrorListener
    0.43
     Pens
    0.42
    landers
    0.42
    Activations Density 4.546%

    No Known Activations