© 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. 14811
    Prev
    Next
    INDEX
    Explanations

    mentions of community and local regions or municipalities

    oai_token-act-pair · gemini-2.0-flash

    local

    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
    enderror
    -0.77
    XmlAccessorType
    -0.55
     NSCoder
    -0.54
    Билгалдахарш
    -0.54
    contentLoaded
    -0.51
    ResponseWriter
    -0.50
    uxxxx
    -0.49
     over
    -0.49
    CompleteListener
    -0.48
    LEncoder
    -0.48
    POSITIVE LOGITS
     fhew
    0.51
    ists
    0.51
     Color
    0.51
     ſtill
    0.50
     ſhe
    0.50
     Monfieur
    0.49
     raiſ
    0.48
    dungen
    0.48
    DebuggerNonUser
    0.48
    равда
    0.47
    Activations Density 6.538%

    No Known Activations