© 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. 103305
    Prev
    Next
    INDEX
    Explanations

    verb endings and characters

    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
    ید
    1.45
    m
    1.38
    ent
    1.29
    res
    1.28
    ed
    1.27
    ag
    1.25
    on
    1.22
    ac
    1.19
    el
    1.16
    i
    1.16
    POSITIVE LOGITS
    ك
    1.36
    га
    1.22
    )=
    1.09
    كار
    1.09
    이었다
    1.05
    ,
    1.01
    ד
    0.98
    이지만
    0.94
    大
    0.93
    Were
    0.93
    Activations Density 0.001%

    No Known Activations