© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3468
    Prev
    Next
    INDEX
    Explanations

    cystic

    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_5_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
    ീയ
    1.74
    -_
    1.71
    ीत
    1.62
    Karena
    1.61
     zato
    1.60
     gagn
    1.59
    যত
    1.57
    elijkheid
    1.57
     sareng
    1.56
    objet
    1.56
    POSITIVE LOGITS
     enraged
    1.72
     Immutable
    1.71
    ر
    1.70
    كت
    1.66
     discernible
    1.63
    ка
    1.63
     evenly
    1.62
    č
    1.62
     overpowering
    1.61
    ꒰
    1.61
    Activations Density 0.000%

    No Known Activations