© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162267
    Prev
    Next
    INDEX
    Explanations

    first and

    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_31_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
    cido
    0.39
     ghosts
    0.39
     posicion
    0.38
     Valores
    0.37
    mez
    0.36
     ollut
    0.36
     Strukt
    0.35
    𝕂
    0.35
     ovaries
    0.35
     সীম
    0.35
    POSITIVE LOGITS
    contin
    0.37
    Continental
    0.36
    Ɩ
    0.36
     சிறந்த
    0.35
    aphosa
    0.35
    ahertz
    0.35
    作物
    0.34
     Европе
    0.34
     йил
    0.34
    explained
    0.33
    Activations Density 0.000%

    No Known Activations