© 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. 6526
    Prev
    Next
    INDEX
    Explanations

    language related to adhering to a standard

    oai_token-act-pair · gemini-2.0-flash

    say "with"

    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
     compliance
    -2.36
    Compliance
    -2.17
     Compliance
    -2.16
    compliance
    -1.94
     comply
    -1.86
     compliant
    -1.77
     complying
    -1.77
     complies
    -1.73
     violation
    -1.73
     violations
    -1.59
    POSITIVE LOGITS
     GenerationType
    0.79
    ActionCreators
    0.75
     Normdatei
    0.64
     समीक्षाओं
    0.52
    audiovisuel
    0.51
    ngdoc
    0.51
    aryen
    0.48
     useContext
    0.47
    Diweddarwch
    0.47
     HttpNotFound
    0.47
    Activations Density 4.756%

    No Known Activations