© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158608
    Prev
    Next
    INDEX
    Explanations

    collide

    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_2_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
    л
    1.53
    تي
    1.29
    р
    1.27
    -
    1.20
    تين
    1.13
    يه
    1.06
    سي
    1.05
    ן
    1.02
    ד
    1.00
    lere
    0.98
    POSITIVE LOGITS
    I
    1.61
     taxonom
    1.26
     bactéri
    1.16
     perdu
    1.14
    اری
    1.12
     demarc
    1.12
     tecnología
    1.08
     fortuit
    1.08
     تک
    1.07
     formación
    1.06
    Activations Density 0.000%

    No Known Activations