© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209694
    Prev
    Next
    INDEX
    Explanations

    eizo, zo, irc, zi, zō

    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_5_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
    )$:
    1.21
     been
    1.13
    )&=
    1.13
    ک
    1.12
    <unused2125>
    1.09
    𝕐
    1.05
    )}=
    1.04
    룺
    1.02
    ۹
    1.02
    л
    1.01
    POSITIVE LOGITS
    ’
    1.92
    2
    1.90
    i
    1.59
    ek
    1.54
    ed
    1.49
    ie
    1.46
    he
    1.45
    '
    1.41
    ной
    1.33
    il
    1.30
    Activations Density 0.000%

    No Known Activations