© 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. 93358
    Prev
    Next
    INDEX
    Explanations

    4

    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
    .
    0.61
    :
    0.48
    y
    0.46
     -
    0.45
    ๗
    0.40
     bandages
    0.40
     suffixes
    0.39
    -"
    0.39
     phasing
    0.37
     -"
    0.37
    POSITIVE LOGITS
    below
    0.69
     above
    0.68
     ABOVE
    0.68
     Above
    0.64
    above
    0.64
     BELOW
    0.63
     below
    0.62
    Above
    0.61
     Below
    0.60
    下面
    0.59
    Activations Density 0.001%

    No Known Activations