© 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. 171028
    Prev
    Next
    INDEX
    Explanations

    fears, phobias, and task aversions

    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
    yno
    0.40
    شاء
    0.38
     Schriftsteller
    0.38
    蝋
    0.37
     salah
    0.37
    Sorting
    0.37
    ribusi
    0.37
    beams
    0.36
    ហ
    0.35
     syntax
    0.35
    POSITIVE LOGITS
    pertoire
    0.45
     orij
    0.43
     aisles
    0.42
     நிறைவே
    0.40
    Incidentally
    0.40
     B
    0.39
     H
    0.39
    ck
    0.38
     Hear
    0.38
    нтен
    0.38
    Activations Density 0.005%

    No Known Activations