© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3306
    Prev
    Next
    INDEX
    Explanations

    code relating to file paths, requests and data management

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    \
    -1.16
    -
    -1.15
    )
    -1.13
    .
    -1.08
    /
    -1.05
    [
    -1.05
    (
    -1.04
    "
    -1.04
    '
    -0.96
    :
    -0.95
    POSITIVE LOGITS
     traditionnels
    0.67
     quelcon
    0.66
     alimentaires
    0.66
     élevés
    0.66
     heureuse
    0.65
     Efq
    0.63
     étoit
    0.63
     colorés
    0.63
     connus
    0.63
     avoient
    0.63
    Activations Density 7.405%

    No Known Activations