© 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. 137773
    Prev
    Next
    INDEX
    Explanations

    turn

    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
     positivity
    0.43
    蒲
    0.40
    ěru
    0.39
    png
    0.39
    assim
    0.38
     physiological
    0.37
     pathos
    0.37
    竦
    0.37
    িং
    0.37
     patho
    0.36
    POSITIVE LOGITS
    Tact
    0.51
     Tact
    0.46
    tact
    0.46
     শাস
    0.43
    coat
    0.43
     Tactical
    0.42
     кот
    0.42
    コート
    0.41
    Kot
    0.41
     verantwortlich
    0.41
    Activations Density 0.001%

    No Known Activations