© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108997
    Prev
    Next
    INDEX
    Explanations

    ergonomics:

    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_1_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
    of
    1.84
    ing
    1.41
    g
    1.32
    ும்
    1.31
    ق
    1.23
    j
    1.23
    h
    1.22
     of
    1.18
    ag
    1.13
    q
    1.10
    POSITIVE LOGITS
    settes
    1.03
    naie
    1.01
     прове
    0.97
     aplicativos
    0.94
    hauses
    0.94
    нус
    0.93
    s
    0.92
     shabby
    0.91
    твор
    0.91
     florals
    0.90
    Activations Density 0.000%

    No Known Activations