© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11488
    Prev
    Next
    INDEX
    Explanations

    praises for basketball players related to specific teams

    oai_token-act-pair · gemini-2.0-flash

    surprise words or uncommon proper nouns

    np_token-act-pair-logits · gpt-4o-mini

    Sports-related content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     مشين
    -0.59
     ModelExpression
    -0.52
    TagMode
    -0.50
     AssemblyCulture
    -0.49
    তথ্যসূত্র
    -0.47
     BoxFit
    -0.45
    strains
    -0.45
     ContentValues
    -0.45
    astify
    -0.44
     relâche
    -0.44
    POSITIVE LOGITS
    neux
    0.60
    rowave
    0.59
    UMBIA
    0.58
    Neem
    0.54
    GeoNames
    0.53
     Borges
    0.52
    vimos
    0.52
     moderation
    0.52
    typeorm
    0.52
     Hard
    0.51
    Activations Density 1.208%

    No Known Activations