© 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. 3280
    Prev
    Next
    INDEX
    Explanations

    code blocks and potentially code documentation.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    styleType
    -0.86
    extAlignment
    -0.77
    IBOutlet
    -0.77
    providedIn
    -0.74
    #+#
    -0.72
    UserScript
    -0.70
     Wicidata
    -0.66
    parsedMessage
    -0.65
     suivants
    -0.65
    }*/
    -0.64
    POSITIVE LOGITS
    erah
    0.47
     Bir
    0.46
     ($
    0.42
    hyrchwyd
    0.42
     ('
    0.42
     #
    0.41
     Fog
    0.41
     '#
    0.40
     "#
    0.40
    "#
    0.40
    Activations Density 2.524%

    No Known Activations