© 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. 211199
    Prev
    Next
    INDEX
    Explanations

    likh, diye, dekha, deti, le li, do

    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
    ’
    1.30
    ला
    1.28
    annya
    1.26
    مان
    1.19
    м
    1.14
    se
    1.13
    지
    1.12
    ють
    1.11
    ants
    1.06
    ό
    1.05
    POSITIVE LOGITS
    0
    1.34
    t
    1.22
     are
    1.19
    "}
    1.15
    ৩৩
    1.14
    ৩৯
    1.13
    ৪২
    1.13
    3
    1.10
     powied
    1.09
    ৩৭
    1.09
    Activations Density 0.000%

    No Known Activations