© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141586
    Prev
    Next
    INDEX
    Explanations

    Apple cider vinegar

    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
     Conce
    0.31
     N
    0.29
     honest
    0.28
     Age
    0.28
     Nhà
    0.28
     Vocational
    0.28
    ーズ
    0.27
     Multin
    0.26
    Ao
    0.26
     U
    0.26
    POSITIVE LOGITS
    itamento
    0.30
    riente
    0.28
    kgs
    0.28
     fermentum
    0.27
    USTER
    0.27
     buddhav
    0.27
     trataro
    0.27
    水的
    0.27
    inete
    0.26
     styleUrls
    0.26
    Activations Density 0.000%

    No Known Activations