© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104404
    Prev
    Next
    INDEX
    Explanations

    how to verb

    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_1_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
    ,
    1.34
     assass
    1.20
     for
    1.20
    4
    1.19
    :
    1.16
    ار
    1.10
    רת
    1.10
     wpły
    1.09
     an
    1.08
     νέ
    1.08
    POSITIVE LOGITS
    t
    1.16
    cknowled
    0.96
    できます
    0.91
    g
    0.80
    ても
    0.75
    le
    0.75
    sc
    0.75
    𝐝
    0.75
    Lemma
    0.74
    da
    0.73
    Activations Density 0.064%

    No Known Activations