© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214552
    Prev
    Next
    INDEX
    Explanations

    the core of

    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_5_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
    k
    1.45
     as
    1.43
    r
    1.42
    n
    1.40
    the
    1.24
    ם
    1.24
    ня
    1.18
    to
    1.17
    ного
    1.17
    ك
    1.13
    POSITIVE LOGITS
    ای
    1.05
    상은
    0.95
     बिज़
    0.94
    い
    0.92
     nàng
    0.88
    ung
    0.87
    Ts
    0.87
    TEM
    0.87
     것은
    0.87
     FODC
    0.86
    Activations Density 0.001%

    No Known Activations