© 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. 10967
    Prev
    Next
    INDEX
    Explanations

    words related to games, opinions, stories, and general statements.

    oai_token-act-pair · gemini-2.0-flash

    Past tense verbs

    np_max-act-logits · 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
    AutoScaleMode
    -0.81
    Sucesor
    -0.68
    Дереккөздер
    -0.67
    jsxFileName
    -0.61
    Erreferentziak
    -0.59
    曖昧さ回避
    -0.59
    webElementXpaths
    -0.57
     OFDb
    -0.55
    Rujuakan
    -0.54
     Roskov
    -0.54
    POSITIVE LOGITS
     recovered
    0.59
     effected
    0.58
     drafted
    0.57
    addPreferredGap
    0.57
     invented
    0.56
    listFiles
    0.56
     developed
    0.56
     built
    0.54
     وتسجيلات
    0.53
     imagined
    0.52
    Activations Density 21.267%

    No Known Activations