© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11332
    Prev
    Next
    INDEX
    Explanations

    instances of phrases containing the words "starting", "initial", or "basic" along with "point", "start", "from", "is", or "assumed", often related to a new beginning or assumption as a foundation

    oai_token-act-pair · gemini-2.0-flash

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     dandy
    -0.79
     myſelf
    -0.77
     Hift
    -0.75
     snippetHide
    -0.73
     plufieurs
    -0.71
     onBackPressed
    -0.71
     tombé
    -0.70
     ResponseEntity
    -0.70
     BoxDecoration
    -0.69
     strconv
    -0.69
    POSITIVE LOGITS
     base
    0.77
    base
    0.63
     Base
    0.57
    <bos>
    0.57
     premise
    0.56
     assume
    0.55
    Base
    0.53
     bases
    0.52
    bases
    0.50
    的基础
    0.50
    Activations Density 1.644%

    No Known Activations