© 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. 229214
    Prev
    Next
    INDEX
    Explanations

    'o' sound

    np_max-act-logits · gemini-2.5-flash-lite
    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
     Wolver
    0.40
    ี
    0.39
     பயன்படுத்த
    0.38
    ার্থী
    0.38
    acker
    0.36
     torture
    0.36
     ಸಾಕಷ್ಟು
    0.36
    ivalence
    0.36
    棂
    0.35
    နိုင်
    0.35
    POSITIVE LOGITS
    𝒐
    0.68
    ⲟ
    0.66
    ɔ
    0.63
    о
    0.62
    𝓸
    0.61
    𝙤
    0.61
    ോ
    0.60
    ᧐
    0.60
    𝗼
    0.60
    وف
    0.59
    Activations Density 0.033%

    No Known Activations