© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17874
    Prev
    Next
    INDEX
    Explanations

    spin states

    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
     excit
    0.46
     exc
    0.45
     에
    0.44
     beach
    0.43
     exchange
    0.42
     Exchange
    0.41
     Ex
    0.40
     Stars
    0.40
    retch
    0.40
     ACE
    0.39
    POSITIVE LOGITS
    трон
    0.39
    Tau
    0.39
    🐁
    0.38
    робнее
    0.37
    Parallel
    0.36
     inversion
    0.36
     pluripotent
    0.36
    cijas
    0.35
    tolyl
    0.35
    ሙ
    0.35
    Activations Density 0.024%

    No Known Activations