© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11958
    Prev
    Next
    INDEX
    Explanations

    words/phrases indicating a high degree of something or adverbs describing a state.

    oai_token-act-pair · gemini-2.0-flash

    highly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -0.57
     Paste
    -0.48
    بوابة
    -0.45
     disambiguazione
    -0.45
    يديا
    -0.45
     الاطلاع
    -0.44
    PIA
    -0.43
     aco
    -0.42
    ніципалі
    -0.42
    stad
    -0.42
    POSITIVE LOGITS
     BorderRadius
    0.69
    nocześnie
    0.68
     GlobalKey
    0.65
    $")
    0.65
    EndInit
    0.65
     صوتيه
    0.65
    WEBPACK
    0.62
    jsonwebtoken
    0.60
     miễn
    0.59
    numerusform
    0.59
    Activations Density 3.248%

    No Known Activations