© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 107
    Prev
    Next
    INDEX
    Explanations

    the word "hand(s)" or "hand-" optionally followed by another word

    oai_token-act-pair · gemini-2.0-flash

    hand

    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
     hand
    -0.96
    hand
    -0.81
    Hand
    -0.79
     Hand
    -0.79
    HAND
    -0.69
    RegressionTest
    -0.69
     HAND
    -0.67
    windowFixed
    -0.65
    evos
    -0.63
    PreferredItem
    -0.62
    POSITIVE LOGITS
    flex
    0.56
    ISTO
    0.55
    TagHelpers
    0.54
     pracu
    0.53
     Spaniard
    0.52
    msgid
    0.52
    bootstrapcdn
    0.51
     détaillés
    0.50
     ankles
    0.50
    ResponseWriter
    0.50
    Activations Density 7.928%

    No Known Activations