© 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. 151261
    Prev
    Next
    INDEX
    Explanations

    say class

    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
    =
    0.54
    f
    0.47
    in
    0.46
     =
    0.45
    e
    0.44
    us
    0.44
    yr
    0.44
    t
    0.44
    =\
    0.43
     LD
    0.43
    POSITIVE LOGITS
    )...
    0.45
     placée
    0.42
     moreover
    0.42
    )…
    0.41
    )....
    0.41
    그래서
    0.40
     данни
    0.40
     даних
    0.40
     garagem
    0.39
     contribut
    0.39
    Activations Density 0.001%

    No Known Activations