© 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. 3467
    Prev
    Next
    INDEX
    Explanations

    text related to folklore, especially Scottish folklore

    oai_token-act-pair · gemini-2.0-flash

    proper nouns and metadata

    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
    ForValue
    -0.64
     SimpleName
    -0.60
    <>());
    -0.54
    verwijspagina
    -0.53
     mergeFrom
    -0.52
     setuptools
    -0.51
    )++;
    -0.51
    كويكب
    -0.50
     absl
    -0.50
     Chaco
    -0.50
    POSITIVE LOGITS
    +#+
    0.65
    IsContent
    0.64
     Alamofire
    0.60
     Galbraith
    0.59
     Laird
    0.57
     MainAxisSize
    0.56
    httphttps
    0.56
     CanadaChoose
    0.56
     Cameron
    0.55
    </thead>
    0.55
    Activations Density 1.930%

    No Known Activations