© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4160
    Prev
    Next
    INDEX
    Explanations

    code snippets and configuration file syntax, especially with code diffs and variable assignments

    oai_token-act-pair · gemini-2.0-flash

    reflexive pronouns

    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
    MessageOf
    -0.71
    GEBURTSDATUM
    -0.69
    hoeddwyd
    -0.65
     متعلقه
    -0.63
    PerformLayout
    -0.61
    ogia
    -0.61
     <=",
    -0.61
    tidae
    -0.58
    mobileqq
    -0.57
    
    -0.57
    POSITIVE LOGITS
     myſelf
    0.81
     itſelf
    0.76
     Reſ
    0.72
     ***/
    0.71
     Jefus
    0.71
    ſelf
    0.70
     raiſ
    0.69
     whoſe
    0.69
     */;
    0.69
     himſelf
    0.68
    Activations Density 26.502%

    No Known Activations