© 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. 6843
    Prev
    Next
    INDEX
    Explanations

    sentences with mathematical and scientific reasoning, often using equations, data, and logical operators.

    oai_token-act-pair · gemini-2.0-flash

    math problems

    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
    bootstrapcdn
    -1.09
    DockStyle
    -1.03
    ]='\
    -0.99
    stateProvider
    -0.98
    WriteTagHelper
    -0.97
    gameserver
    -0.97
    addCriterion
    -0.95
    StandardCharsets
    -0.94
    UserScript
    -0.94
     盗撮
    -0.93
    POSITIVE LOGITS
    <bos>
    0.17
     flesta
    0.14
     judiciales
    0.07
     enfans
    0.05
     civiles
    0.04
     sociala
    0.03
     bílá
    0.03
     gamla
    0.03
     gräns
    0.03
     tidigare
    0.02
    Activations Density 76.518%

    No Known Activations