© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9276
    Prev
    Next
    INDEX
    Explanations

    else

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    いていた
    0.81
     vascul
    0.77
     Xamarin
    0.74
    斓
    0.74
     Farn
    0.73
     decía
    0.71
     sapon
    0.71
     cioc
    0.71
     Scan
    0.70
     brinc
    0.69
    POSITIVE LOGITS
     बचत
    0.61
    featured
    0.60
    물의
    0.56
    বহুল
    0.56
    జ్య
    0.56
     হাউ
    0.56
     }^{(
    0.55
    go
    0.55
    物
    0.55
    bedaan
    0.55
    Activations Density 0.006%

    No Known Activations