© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98056
    Prev
    Next
    INDEX
    Explanations

    `view` / `returns`

    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_14_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
     homestead
    0.55
     dorm
    0.54
     VIDEO
    0.53
     quarters
    0.52
     publicar
    0.52
     homecoming
    0.52
    l
    0.52
     ப
    0.50
     odlu
    0.50
     editorial
    0.50
    POSITIVE LOGITS
    specificity
    0.54
    coord
    0.52
    дя
    0.52
    ંતુ
    0.51
    rotate
    0.50
    enfant
    0.50
    peu
    0.50
    aconit
    0.50
    上で
    0.49
    translateX
    0.49
    Activations Density 0.000%

    No Known Activations