© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129441
    Prev
    Next
    INDEX
    Explanations

    zilla, Gret, rest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    ﻮ
    0.71
    ﺪ
    0.68
    ές
    0.65
     ಔಷಧ
    0.63
     korišten
    0.62
     seguir
    0.62
     quell
    0.61
    ﻟ
    0.60
    ید
    0.58
    らの
    0.57
    POSITIVE LOGITS
    ت
    1.07
    u
    0.88
           
    0.87
                
    0.85
    ur
    0.84
     assays
    0.80
    '
    0.77
    /
    0.76
    _
    0.75
    ties
    0.75
    Activations Density 0.000%

    No Known Activations