© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57762
    Prev
    Next
    INDEX
    Explanations

    Ку

    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
    ness
    0.38
     anything
    0.38
     oo
    0.37
     rada
    0.36
     zami
    0.36
     radiolysis
    0.36
     topper
    0.36
    ه
    0.36
    oo
    0.36
    ie
    0.35
    POSITIVE LOGITS
     СО
    0.51
    Sob
    0.47
    formas
    0.46
    со
    0.46
    sob
    0.44
     Sob
    0.44
     SOA
    0.43
    Prest
    0.42
    цен
    0.42
    Ṕ
    0.42
    Activations Density 0.000%

    No Known Activations