© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107456
    Prev
    Next
    INDEX
    Explanations

    bijection

    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
    ם
    1.96
    م
    1.72
    ל
    1.48
    не
    1.44
    в
    1.44
    ور
    1.35
    ل
    1.34
    ম
    1.33
    ت
    1.33
    ুল
    1.30
    POSITIVE LOGITS
    '),
    1.29
    <0x80>
    1.20
    0
    1.15
    ’
    1.12
    )&=
    1.08
    \'
    1.07
    '],
    1.05
    ja
    1.03
    ')$
    1.03
     that
    1.02
    Activations Density 0.000%

    No Known Activations