© 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. 5666
    Prev
    Next
    INDEX
    Explanations

    words related to personal decision-making

    oai_token-act-pair · gemini-2.0-flash

    unique or uncommon terms and formats

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

    random text excerpts

    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
     acted
    -1.11
     walked
    -1.03
     proceeded
    -1.00
     responded
    -0.99
     interacted
    -0.98
     reacted
    -0.98
     showed
    -0.97
     kept
    -0.97
     looked
    -0.94
     stood
    -0.94
    POSITIVE LOGITS
    tvguidetime
    0.73
     purpoſe
    0.63
     Efq
    0.59
    Uwagi
    0.59
     GIPHY
    0.58
     uſe
    0.57
    醐
    0.53
    DeleteBehavior
    0.52
     cauſe
    0.52
    Öffnungszeiten
    0.52
    Activations Density 3.670%

    No Known Activations