© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210351
    Prev
    Next
    INDEX
    Explanations

    what's working and what's not

    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_20_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
     descuento
    0.45
    聿
    0.45
     القسمه
    0.45
     стрель
    0.44
    ભ્ય
    0.44
     teles
    0.43
    skih
    0.43
     करार
    0.42
    رش
    0.42
     같습니다
    0.41
    POSITIVE LOGITS
    (
    0.50
     (
    0.45
     P
    0.44
    G
    0.44
     pour
    0.43
     }(
    0.43
     przez
    0.42
     avec
    0.42
    activating
    0.41
     Proses
    0.41
    Activations Density 0.002%

    No Known Activations