© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 354
    Prev
    Next
    INDEX
    Explanations

    descriptions of robots or armored characters and their suits.

    oai_token-act-pair · gemini-2.0-flash

    Character descriptions from Kyuranger series

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    hyrchwyd
    -0.69
    webElementXpaths
    -0.66
    PhysRevD
    -0.66
    LookAnd
    -0.64
     HasFactory
    -0.59
     bezeichneter
    -0.55
    tagHelperRunner
    -0.55
    bandcamp
    -0.55
     мәкал
    -0.55
    θος
    -0.52
    POSITIVE LOGITS
    KommentareTeilen
    0.57
    脚注の使い方
    0.53
    Gem
    0.50
     Numa
    0.50
     nullptr
    0.49
    NULL
    0.47
    )(((
    0.46
    enumi
    0.46
     crucible
    0.45
     NULL
    0.45
    Activations Density 12.388%

    No Known Activations