© 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. 1128
    Prev
    Next
    INDEX
    Explanations

    location, area or districts

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    RectangleBorder
    -0.73
     AssemblyProduct
    -0.69
    sidemargin
    -0.66
    UnknownFieldSet
    -0.65
     esternos
    -0.64
     verheiratet
    -0.63
     veda
    -0.63
    thâu
    -0.62
    ScopeManager
    -0.60
     tfsi
    -0.59
    POSITIVE LOGITS
     getIs
    0.58
     compito
    0.55
     thuốc
    0.54
     journaux
    0.54
     getC
    0.53
     tỷ
    0.53
     singoli
    0.53
     hommes
    0.52
    stam
    0.51
    unen
    0.51
    Activations Density 0.458%

    No Known Activations