© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177404
    Prev
    Next
    INDEX
    Explanations

    end of function definitions

    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_24_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
    Numerator
    0.40
    ազ
    0.37
     assuntos
    0.37
    伉
    0.37
     cantidad
    0.36
    ㄸ
    0.36
    cantidad
    0.36
    %。
    0.35
    UAE
    0.35
     quantidades
    0.35
    POSITIVE LOGITS
     ironic
    0.45
     wry
    0.43
     succinctly
    0.42
    venir
    0.42
     irony
    0.41
    pec
    0.41
     selectable
    0.41
     SM
    0.40
     hat
    0.40
     blatant
    0.40
    Activations Density 0.001%

    No Known Activations