© 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. 3484
    Prev
    Next
    INDEX
    Explanations

    send requests and messages

    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
    о
    2.25
    та
    1.82
    после
    1.74
    schaft
    1.55
     sporo
    1.53
     ";"
    1.50
     financeira
    1.49
     अंतर्गत
    1.48
     cbind
    1.48
     priori
    1.46
    POSITIVE LOGITS
     chóng
    2.06
    ţa
    1.93
     chills
    1.86
    ța
    1.85
    💨
    1.80
    wreck
    1.77
     vomiting
    1.75
    giving
    1.72
    wiches
    1.69
    轫
    1.69
    Activations Density 0.064%

    No Known Activations