© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111906
    Prev
    Next
    INDEX
    Explanations

    circumnavigate or innovate

    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_2_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
    ,
    1.17
    .
    1.07
    ति
    1.03
    /
    0.98
     organis
    0.96
     on
    0.95
    ires
    0.92
    سم
    0.92
    ного
    0.91
    ens
    0.89
    POSITIVE LOGITS
    の後
    1.27
    ا
    1.25
    این
    1.24
    ال
    1.23
    اا
    1.21
    اً
    1.20
    的作品
    1.20
    ﻥ
    1.18
    ມັນ
    1.17
    اك
    1.13
    Activations Density 0.000%

    No Known Activations