© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54417
    Prev
    Next
    INDEX
    Explanations

    inches, cm, mm, bx, pk

    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_30_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
    ledged
    0.21
    }|\
    0.18
    гли
    0.18
     כת
    0.18
     Holliday
    0.18
    =-\
    0.17
    ^^^^
    0.17
    ><
    0.17
    สำเร็จ
    0.17
     COMMUN
    0.17
    POSITIVE LOGITS
     matéria
    0.22
    诺
    0.21
     boxing
    0.20
     boxe
    0.20
     penyakit
    0.20
     estet
    0.20
     Boxing
    0.20
    Boxing
    0.20
    ុំ
    0.19
    ötet
    0.19
    Activations Density 0.001%

    No Known Activations