© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12351
    Prev
    Next
    INDEX
    Explanations

    code characters such as "this.", numbers, and specific variable names

    oai_token-act-pair · gemini-2.0-flash

    this, 0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     hung
    -0.50
     مج
    -0.48
     ged
    -0.47
     M
    -0.47
     most
    -0.47
     Hanging
    -0.45
     hanging
    -0.44
     Ra
    -0.44
     conf
    -0.43
     vo
    -0.43
    POSITIVE LOGITS
     wireType
    0.86
    IntoConstraints
    0.82
    Personendaten
    0.82
     pleaſure
    0.79
    Tikang
    0.78
     kaarangay
    0.78
     houſe
    0.78
    +#+#
    0.76
    ConstraintMaker
    0.75
     ſtate
    0.75
    Activations Density 0.062%

    No Known Activations