© 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. 67139
    Prev
    Next
    INDEX
    Explanations

    model acknowledgment

    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
    撗
    0.42
     Mobility
    0.39
    itos
    0.38
     dere
    0.36
    ΙΑ
    0.36
     ata
    0.35
    enste
    0.35
     $_{\
    0.35
     gu
    0.35
    சொ
    0.35
    POSITIVE LOGITS
    pentine
    0.45
    RNA
    0.43
    百貨
    0.37
    RSA
    0.36
    するか
    0.36
     RNA
    0.36
    Teri
    0.36
    修订
    0.36
     Lincoln
    0.36
    Grady
    0.36
    Activations Density 0.018%

    No Known Activations