© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112677
    Prev
    Next
    INDEX
    Explanations

    turns to

    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_2_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
     The
    1.11
     to
    1.05
    "
    1.00
     t
    0.99
    The
    0.98
    ت
    0.97
    d
    0.96
    (
    0.96
    0
    0.94
     on
    0.88
    POSITIVE LOGITS
    い
    1.38
    ன்
    1.23
    ਾ
    1.23
    י
    1.09
    ي
    1.09
    ı
    1.08
    ва
    1.07
    я
    1.03
    ী
    1.03
    ാ
    1.03
    Activations Density 0.001%

    No Known Activations