© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236262
    Prev
    Next
    INDEX
    Explanations

    say "acidic"

    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_46_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
    鵜
    0.44
     organization
    0.39
     پان
    0.39
     Jwt
    0.38
     binaries
    0.37
     संख्याओं
    0.37
     knelt
    0.37
    빱
    0.37
     FB
    0.36
     تي
    0.36
    POSITIVE LOGITS
     acidic
    2.59
     acid
    2.58
     Acid
    2.50
    Acid
    2.48
    酸
    2.36
    acid
    2.30
     acidity
    2.06
     acide
    1.98
     ACID
    1.97
     acids
    1.93
    Activations Density 0.001%

    No Known Activations