© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122134
    Prev
    Next
    INDEX
    Explanations

    fuel pellets, FuelCell, farming, Association

    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_3_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
    in
    1.04
    ين
    0.91
    ва
    0.89
    a
    0.89
    า
    0.82
    ta
    0.79
    g
    0.76
    ed
    0.76
    मधील
    0.74
    n
    0.74
    POSITIVE LOGITS
    İ
    0.86
    0.73
     n
    0.68
    С
    0.66
    กับการ
    0.66
     всё
    0.66
    </h3>
    0.65
    ली
    0.65
    ILLA
    0.64
    จะ
    0.63
    Activations Density 0.005%

    No Known Activations