© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14856
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Deletions or ignored items

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    structors
    -0.79
    ])));
    -0.75
    ]]
    -0.69
     BoxFit
    -0.64
    )•
    -0.64
    '))
    -0.63
    extAlignment
    -0.63
    deals
    -0.61
    BuilderFactory
    -0.61
    )]
    -0.60
    POSITIVE LOGITS
    DELETED
    0.60
    unauthorized
    0.57
    IGNORE
    0.57
    nearest
    0.56
     autorisés
    0.56
    Useless
    0.55
    Abandoned
    0.53
    Unauthorized
    0.53
    Lowest
    0.53
    Missed
    0.52
    Activations Density 9.929%

    No Known Activations