© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211298
    Prev
    Next
    INDEX
    Explanations

    False, great, Dev, Less, Op

    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
    0
    1.37
    {
    1.35
    ;
    1.29
    5
    1.12
    1
    1.06
    s
    1.05
    𝐬
    1.02
    \
    1.01
     for
    1.00
    de
    0.99
    POSITIVE LOGITS
    いた
    1.26
    א
    1.20
     हुए
    1.10
    אן
    1.10
    می
    1.06
    ’
    1.05
    ными
    0.98
    合った
    0.98
     Ż
    0.97
    는
    0.96
    Activations Density 0.007%

    No Known Activations