© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236866
    Prev
    Next
    INDEX
    Explanations

    helpful/correct feedback

    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_32_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
     tempted
    0.42
    रीन
    0.41
    bibfield
    0.40
    тории
    0.39
     nano
    0.39
     harp
    0.39
     raro
    0.38
    皁
    0.38
     voluntary
    0.37
    юнча
    0.37
    POSITIVE LOGITS
     rejected
    0.40
     dissatisfaction
    0.40
     Becoming
    0.40
     disliked
    0.40
     Transition
    0.39
     Rejected
    0.39
     Struggles
    0.38
     Agreed
    0.37
    Rejected
    0.36
     Electrode
    0.36
    Activations Density 0.000%

    No Known Activations