© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53539
    Prev
    Next
    INDEX
    Explanations

    salt

    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_55_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
     salt
    2.39
    salt
    2.22
    Salt
    2.19
     Salt
    2.14
     SALT
    1.86
    盐
    1.81
    鹽
    1.80
    SALT
    1.73
    塩
    1.66
     salts
    1.52
    POSITIVE LOGITS
     경
    0.44
    ็ง
    0.36
    Crist
    0.35
    泛
    0.35
     निबंध
    0.35
    หนัก
    0.35
     nặng
    0.35
     сказала
    0.35
    楇
    0.35
     Crist
    0.34
    Activations Density 0.003%

    No Known Activations