© 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. 130728
    Prev
    Next
    INDEX
    Explanations

    HTML span and inline tags

    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
    ja
    0.86
    J
    0.84
    0.80
     siden
    0.73
     digraph
    0.73
     been
    0.73
     $
    0.72
     by
    0.72
            
    0.71
     http
    0.71
    POSITIVE LOGITS
    ین
    0.86
    ERS
    0.85
    форми
    0.79
    یر
    0.77
    𝗨
    0.75
    ﻒ
    0.73
    ﺲ
    0.73
    of
    0.73
    مک
    0.73
    ни
    0.72
    Activations Density 0.000%

    No Known Activations