© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16056
    Prev
    Next
    INDEX
    Explanations

    board meetings and resolutions

    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_15_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
    keV
    0.40
     अध्यापक
    0.37
    𝑽
    0.34
    セプト
    0.32
     पुण्य
    0.32
    વાસ
    0.32
     ఆర్థిక
    0.32
    ྭ
    0.31
    rikt
    0.31
    vée
    0.31
    POSITIVE LOGITS
     about
    0.35
    ی
    0.33
     بتق
    0.32
     knives
    0.32
     ktore
    0.32
     which
    0.31
    يط
    0.31
    ي
    0.31
     needs
    0.31
     where
    0.30
    Activations Density 0.003%

    No Known Activations