© 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. 150567
    Prev
    Next
    INDEX
    Explanations

    Ups

    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
    úp
    0.42
    localVarPath
    0.40
     Modes
    0.38
     oby
    0.37
    ó
    0.37
    ணமாக
    0.37
    hk
    0.35
     অথচ
    0.35
    desert
    0.35
    igo
    0.35
    POSITIVE LOGITS
     fluttering
    0.40
     vanishing
    0.40
     fading
    0.39
     gladly
    0.39
     lasted
    0.38
     darken
    0.38
    𝓲
    0.38
    itat
    0.38
     multitude
    0.37
    vanishing
    0.37
    Activations Density 0.009%

    No Known Activations