© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233008
    Prev
    Next
    INDEX
    Explanations

    connecting contrasting ideas

    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_32_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
     nhau
    0.42
    ፣
    0.36
    じる
    0.35
    ,#
    0.33
    dings
    0.32
    雖然
    0.32
    雖
    0.32
     scrap
    0.32
     approaching
    0.31
     zipper
    0.31
    POSITIVE LOGITS
     nimeni
    0.40
    𒈾
    0.38
     所以
    0.36
     ezért
    0.36
    RAD
    0.35
    渎
    0.35
     sabot
    0.35
    oxin
    0.34
     Dlatego
    0.34
     Tất
    0.34
    Activations Density 0.000%

    No Known Activations