© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88578
    Prev
    Next
    INDEX
    Explanations

    separators or headers

    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_23_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
    ൺ
    0.40
     جميعا
    0.38
    ണ്‍
    0.37
     וב
    0.36
     Nonetheless
    0.36
    Renk
    0.36
     strained
    0.35
    𝑛
    0.35
     affirme
    0.35
    ارين
    0.35
    POSITIVE LOGITS
    gif
    0.36
     Đặc
    0.36
    scss
    0.36
     GOVERNMENT
    0.35
    里的
    0.35
     편
    0.35
     художе
    0.35
     scala
    0.34
    碌
    0.34
     relaxing
    0.34
    Activations Density 0.000%

    No Known Activations