© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58129
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    ниця
    0.41
     eines
    0.38
     }(
    0.38
     energetically
    0.36
     Fun
    0.36
    евского
    0.36
     fiery
    0.36
    цы
    0.35
    纪
    0.34
    마트
    0.34
    POSITIVE LOGITS
     wins
    0.60
     kindly
    0.56
    wins
    0.50
     Kindly
    0.49
    Kindly
    0.47
    Wins
    0.47
     Wins
    0.43
     tooth
    0.42
    cred
    0.41
     offic
    0.41
    Activations Density 0.152%

    No Known Activations