© 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. 17584
    Prev
    Next
    INDEX
    Explanations

    closing the gap

    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
    dfe
    0.41
    夏季
    0.39
     antid
    0.37
    帀
    0.37
    保护
    0.36
     contradiction
    0.36
    保護
    0.35
    }}=(
    0.35
     सूची
    0.34
    ratings
    0.34
    POSITIVE LOGITS
     gain
    0.53
     Gain
    0.52
     Catch
    0.50
     catching
    0.49
     catch
    0.48
    Catch
    0.47
    gain
    0.47
     gains
    0.44
    Gain
    0.42
     gained
    0.42
    Activations Density 0.087%

    No Known Activations