© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147972
    Prev
    Next
    INDEX
    Explanations

    s

    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_59_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
     가
    0.77
     Га
    0.54
     Ga
    0.52
     गा
    0.52
    Га
    0.51
     Gail
    0.51
     Gaw
    0.51
    Ga
    0.50
     something
    0.49
     Gat
    0.49
    POSITIVE LOGITS
     worthwhile
    0.68
     worthless
    0.45
     Pulse
    0.39
    Weak
    0.37
    ')]
    0.35
     усі
    0.35
     سقوط
    0.35
    )]
    0.34
     Είναι
    0.34
     serio
    0.34
    Activations Density 0.004%

    No Known Activations