© 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. 8853
    Prev
    Next
    INDEX
    Explanations

    the letter "A" often followed by articles, prepositions, or codes

    oai_token-act-pair · gemini-2.0-flash

    A

    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
     виправивши
    -0.75
    InjectAttribute
    -0.65
    protoimpl
    -0.61
    "},
    -0.60
    '],
    -0.59
     the
    -0.59
     متعلقه
    -0.59
    '},
    -0.58
    mittelt
    -0.58
    .",
    -0.57
    POSITIVE LOGITS
     lot
    1.93
    lot
    1.43
     Lot
    1.38
    Lot
    1.38
     LOT
    1.30
     lots
    1.20
    lots
    1.13
    LOT
    1.13
     Lots
    1.10
    Lots
    1.01
    Activations Density 3.075%

    No Known Activations