© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8565
    Prev
    Next
    INDEX
    Explanations

    single capitalized letters or short abbreviations

    oai_token-act-pair · 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
    UnknownFields
    -0.52
    <bos>
    -0.48
    oa̍t
    -0.47
     '\\;'
    -0.47
    ținut
    -0.47
    nellement
    -0.47
     INTERESAR
    -0.47
    j
    -0.46
    ToRefresh
    -0.45
    aéroport
    -0.45
    POSITIVE LOGITS
    UPAC
    0.65
    ritsar
    0.59
    raits
    0.59
    enough
    0.55
    foundland
    0.52
    aragus
    0.52
    memoized
    0.50
    ldg
    0.50
    copyWith
    0.50
    fficients
    0.49
    Activations Density 2.666%

    No Known Activations