© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78600
    Prev
    Next
    INDEX
    Explanations

    eff followed by words like efface, effondrent, effekte, effizienz

    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_0_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
    ل
    1.73
    ت
    1.73
    ז
    1.58
    ین
    1.53
    ५
    1.48
    ित
    1.47
    ad
    1.45
    ル
    1.45
    л
    1.44
    ᱓
    1.42
    POSITIVE LOGITS
    -
    1.36
    ช่วง
    1.32
    க்கு
    1.27
    大气
    1.26
     (
    1.22
    يا
    1.22
    ти
    1.20
    కి
    1.18
    ออก
    1.18
    1.15
    Activations Density 0.002%

    No Known Activations