© 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. 8763
    Prev
    Next
    INDEX
    Explanations

    saving checkpoints

    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
     Held
    0.39
    ozu
    0.39
     reset
    0.36
    饱
    0.35
     Socket
    0.35
     Reset
    0.35
    Reset
    0.34
     सत्य
    0.34
    要求的
    0.34
    nsen
    0.34
    POSITIVE LOGITS
    Karo
    0.48
    ኽ
    0.41
     karo
    0.39
     Karo
    0.39
     sauvegarde
    0.38
     मार्क्स
    0.37
    issions
    0.36
    amination
    0.36
    КП
    0.34
    ट्यूब
    0.34
    Activations Density 0.001%

    No Known Activations