© 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. 107307
    Prev
    Next
    INDEX
    Explanations

    congruent or ray

    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
    ab
    1.27
    in
    1.12
    io
    1.02
    ↵↵
    0.99
    ia
    0.98
    ib
    0.96
    p
    0.89
    iv
    0.88
    la
    0.88
    m
    0.87
    POSITIVE LOGITS
    Д
    1.17
    Да
    1.16
    ன்
    1.16
    ют
    1.09
    ός
    1.05
    Мо
    1.04
    ¹.
    1.03
    ма
    1.02
    Ту
    1.02
     перспек
    1.02
    Activations Density 0.000%

    No Known Activations