© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84336
    Prev
    Next
    INDEX
    Explanations

    inherent dignity

    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_0_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
    l
    1.96
    л
    1.81
    ল
    1.59
    ل
    1.51
     for
    1.36
    st
    1.30
    ث
    1.24
    se
    1.23
    ש
    1.22
    تها
    1.21
    POSITIVE LOGITS
    ।
    1.67
    い
    1.44
    на
    1.33
    માં
    1.31
    서
    1.30
     I
    1.30
    등학교
    1.15
    ?
    1.13
    า
    1.13
    й
    1.12
    Activations Density 0.001%

    No Known Activations