© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5344
    Prev
    Next
    INDEX
    Explanations

    national-helpline numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ся
    1.01
    в
    0.98
    is
    0.97
    Фи
    0.93
    ા
    0.91
    за
    0.91
    er
    0.90
    д
    0.89
    いう
    0.88
    на
    0.87
    POSITIVE LOGITS
     réglementation
    1.26
     rescind
    1.26
     anteced
    1.25
     контак
    1.23
     neutrons
    1.14
    fonte
    1.12
     perhatian
    1.12
    crollView
    1.12
     vlast
    1.11
     ascertained
    1.11
    Activations Density 0.182%

    No Known Activations