© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82342
    Prev
    Next
    INDEX
    Explanations

    see, fulfillment, food, understanding, irrigation, name, algebra

    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_29_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
    eonium
    0.38
    位的
    0.36
    YAN
    0.36
    །
    0.36
    ׁ
    0.35
    実際に
    0.35
    ২২
    0.35
    दक्षिण
    0.35
    声
    0.35
    ⋄
    0.34
    POSITIVE LOGITS
     with
    0.44
     V
    0.41
     temer
    0.41
     ugu
    0.41
     K
    0.40
    lyk
    0.38
    ahanglan
    0.38
     ru
    0.38
     Bela
    0.37
    velt
    0.37
    Activations Density 0.001%

    No Known Activations