© 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. 3476
    Prev
    Next
    INDEX
    Explanations

    cloud and fog conditions

    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
    স্থাপ
    1.48
    েই
    1.45
    i
    1.43
    ি
    1.42
     coinc
    1.39
    യി
    1.36
     véritable
    1.36
    చ్చ
    1.35
     nej
    1.35
    tedir
    1.33
    POSITIVE LOGITS
     highlands
    1.97
     workforce
    1.83
     FirebaseAuth
    1.79
     encoders
    1.76
    霾
    1.74
    correcto
    1.73
    amethasone
    1.70
    ல்
    1.68
     genero
    1.67
    霭
    1.66
    Activations Density 0.097%

    No Known Activations