© 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. 1663
    Prev
    Next
    INDEX
    Explanations

    turning waste into worth

    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
    真的
    0.33
    ="\
    0.33
    趣
    0.32
    真的很
    0.31
    covery
    0.31
    Recovery
    0.31
     REALLY
    0.31
     guts
    0.31
    Bian
    0.30
    厭
    0.30
    POSITIVE LOGITS
     ride
    0.43
     unlocking
    0.42
     Ride
    0.42
     sowing
    0.41
     Unlock
    0.39
     unlock
    0.39
    Ride
    0.37
     rides
    0.36
     riding
    0.36
     debajo
    0.36
    Activations Density 0.066%

    No Known Activations