© 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. 14908
    Prev
    Next
    INDEX
    Explanations

    code file headers

    oai_token-act-pair · gemini-2.0-flash

    computer code/paths/URLs

    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
     Google
    -0.49
    Google
    -0.44
     Urbano
    -0.43
     PB
    -0.43
     WRC
    -0.42
     calculus
    -0.42
     Sénat
    -0.42
     Primaria
    -0.42
    opt
    -0.41
    )":
    -0.41
    POSITIVE LOGITS
    DataAnnotations
    0.95
     متعلقه
    0.84
    ViewFeatures
    0.76
    rungsseite
    0.72
    TabIndex
    0.72
    Cubit
    0.68
    adaptiveStyles
    0.68
    sizeCache
    0.68
    awtextra
    0.68
    GraphicsUnit
    0.66
    Activations Density 3.860%

    No Known Activations