© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92798
    Prev
    Next
    INDEX
    Explanations

    res

    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_60_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
    p
    1.75
    in
    1.45
    pV
    0.84
    pj
    0.77
    pá
    0.77
    pä
    0.77
    pK
    0.76
    pR
    0.75
    pia
    0.74
    på
    0.74
    POSITIVE LOGITS
     pudd
    0.58
     puddle
    0.51
     Dole
    0.51
     Co
    0.48
     Dort
    0.48
     Dol
    0.47
     Pudding
    0.47
     Fram
    0.46
     TestAvg
    0.46
     Obstet
    0.46
    Activations Density 0.001%

    No Known Activations