© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34186
    Prev
    Next
    INDEX
    Explanations

    flipping

    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_7_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
     on
    1.20
     for
    1.09
     at
    0.93
    ulation
    0.90
    iano
    0.90
     et
    0.89
    થ
    0.89
     of
    0.88
     el
    0.88
    ía
    0.88
    POSITIVE LOGITS
    s
    1.09
    lc
    1.02
    ні
    1.01
    ים
    0.99
    lere
    0.98
    lige
    0.97
    ו
    0.97
    ה
    0.97
    אים
    0.96
    lir
    0.96
    Activations Density 0.000%

    No Known Activations