© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232075
    Prev
    Next
    INDEX
    Explanations

    improve

    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_6_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
    1
    1.20
    ’
    1.05
    s
    1.02
    he
    0.98
    ll
    0.91
    3
    0.77
    ing
    0.75
     elektrik
    0.75
    9
    0.75
    th
    0.74
    POSITIVE LOGITS
    ल
    1.28
    ל
    1.27
    ل
    1.23
    ва
    1.02
    л
    0.95
    то
    0.94
    اهای
    0.91
    ิ
    0.88
     взя
    0.86
    ো
    0.84
    Activations Density 0.006%

    No Known Activations