© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176233
    Prev
    Next
    INDEX
    Explanations

    explaining why something should/might happen

    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_20_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
    idegg
    0.43
    )\}
    0.43
     Schaff
    0.41
     Pillars
    0.40
     большинстве
    0.39
    IsNot
    0.39
    itsch
    0.39
     대부분
    0.39
     большинство
    0.39
    棌
    0.39
    POSITIVE LOGITS
     due
    0.46
     由于
    0.44
     harmonize
    0.43
    Due
    0.41
     adjusts
    0.41
     frequently
    0.40
    由于
    0.40
    rawal
    0.40
     Ku
    0.39
    Adjust
    0.39
    Activations Density 0.021%

    No Known Activations