© 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. 11913
    Prev
    Next
    INDEX
    Explanations

    labels in a dataset, specifically those relating to sex and age

    oai_token-act-pair · gemini-2.0-flash

    patient tumor characteristics

    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
    Geplaatst
    -0.66
    الحياه
    -0.54
    Gambas
    -0.47
    parsedMessage
    -0.47
    spender
    -0.46
    حوالہ
    -0.46
    IBOutlet
    -0.45
    bd
    -0.44
    Nuorodos
    -0.43
    EndContext
    -0.43
    POSITIVE LOGITS
     Efq
    0.66
     intStringLen
    0.59
    #+#
    0.59
    :+:
    0.58
    ^(@)
    0.56
    -------
    0.56
    \"");
    0.55
    ựng
    0.55
     $_"
    0.55
     situato
    0.54
    Activations Density 0.235%

    No Known Activations