© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 429
    Prev
    Next
    INDEX
    Explanations

    code-related tokens such as definitions of parameters, classes, and variables.

    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_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
     raiſ
    -0.86
     uſed
    -0.62
     features
    -0.60
     myſelf
    -0.60
     pleaſure
    -0.59
     poffe
    -0.58
     purpoſe
    -0.58
     works
    -0.58
     free
    -0.57
     houſe
    -0.57
    POSITIVE LOGITS
    unauthorized
    0.55
    anonym
    0.53
    applicable
    0.52
    ético
    0.50
    ambiguous
    0.50
    localisation
    0.49
    respective
    0.49
    authorised
    0.49
    equality
    0.48
    degradable
    0.47
    Activations Density 11.303%

    No Known Activations