© 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-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229327
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    Sed
    0.42
    פו
    0.41
    ishan
    0.40
     Gul
    0.38
    ◸
    0.38
     gul
    0.38
    वि
    0.37
    Gul
    0.37
    坠
    0.36
    ंडे
    0.35
    POSITIVE LOGITS
    ns
    0.79
    ンス
    0.56
    nden
    0.55
    den
    0.53
    nst
    0.51
    nsp
    0.51
    mens
    0.47
    NS
    0.47
    ንስ
    0.47
    nder
    0.46
    Activations Density 0.000%

    No Known Activations