© 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. 14898
    Prev
    Next
    INDEX
    Explanations

    descriptions of software updates and bug fixes

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific contexts

    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
     fix
    -1.03
     Fix
    -1.01
    Fix
    -1.00
    fix
    -0.98
     remedy
    -0.87
     cure
    -0.81
    FIX
    -0.81
     FIX
    -0.75
     intervention
    -0.75
     Fixing
    -0.73
    POSITIVE LOGITS
     ModelExpression
    0.64
     виправивши
    0.63
    arraycopy
    0.62
    mpo
    0.55
    UPAC
    0.53
    󠁴
    0.53
    inghouse
    0.53
    IntoConstraints
    0.51
    obiology
    0.51
    Tikang
    0.51
    Activations Density 3.337%

    No Known Activations