© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10878
    Prev
    Next
    INDEX
    Explanations

    make a favor or another

    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_40_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
    पत
    0.39
     जाणून
    0.38
    eking
    0.38
    toon
    0.37
    榨
    0.37
     Schol
    0.37
    eken
    0.36
     सद
    0.36
     eyeshadow
    0.36
    nut
    0.35
    POSITIVE LOGITS
     made
    0.66
    做的
    0.65
     сдела
    0.64
     gemacht
    0.62
    做得
    0.62
    做
    0.61
     делается
    0.60
     done
    0.57
     faite
    0.55
     做
    0.55
    Activations Density 0.009%

    No Known Activations