© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80638
    Prev
    Next
    INDEX
    Explanations

    aspecto específico o apariencia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    つ
    1.59
    用
    1.55
    لي
    1.49
    ৪
    1.46
    드
    1.45
    出発
    1.42
    나
    1.35
    値
    1.34
     نہيں
    1.33
    மொழி
    1.31
    POSITIVE LOGITS
    to
    1.91
    ى
    1.66
    us
    1.63
    the
    1.63
    ong
    1.52
    ok
    1.45
    et
    1.44
    ور
    1.40
    ized
    1.39
     to
    1.38
    Activations Density 0.000%

    No Known Activations