© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146127
    Prev
    Next
    INDEX
    Explanations

    but/however introducing limitations/challenges

    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
    ي
    1.59
    u
    1.54
    י
    1.48
    した
    1.41
    つ
    1.39
    ות
    1.34
     nhàng
    1.30
    ド
    1.29
    TINGS
    1.27
    >′
    1.26
    POSITIVE LOGITS
    r
    2.06
     in
    2.05
     I
    1.74
    ak
    1.63
    ons
    1.56
    s
    1.52
    on
    1.46
    os
    1.44
     on
    1.34
    am
    1.29
    Activations Density 0.000%

    No Known Activations