Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 33-GEMMASCOPE-2-TRANSCODER-262K
    4. 261662
    Prev
    Next
    INDEX
    Explanations

    giving instructions

    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_33_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
     adulti
    0.89
     पुस्तिका
    0.88
    Ke
    0.88
    ع
    0.86
    ২৩
    0.86
    G
    0.86
     পদার্থ
    0.83
     automorphism
    0.82
    M
    0.80
    UNICATIONS
    0.79
    POSITIVE LOGITS
    dang
    1.06
     Immune
    0.99
    lington
    0.97
     گونه
    0.95
     Ears
    0.93
     Sill
    0.91
     Possession
    0.88
     Seguro
    0.87
     Bung
    0.86
     Blood
    0.86
    Activations Density 0.000%

    No Known Activations