© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196540
    Prev
    Next
    INDEX
    Explanations

    -able suffix

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     શાંત
    0.39
     resize
    0.38
    resize
    0.38
     벡터
    0.37
     autod
    0.37
    翟
    0.37
     recreate
    0.37
     brom
    0.36
    brom
    0.36
     נישט
    0.36
    POSITIVE LOGITS
     قابل
    1.63
    可
    1.27
     Iterable
    1.23
    readable
    1.22
     readable
    1.19
    ible
    1.18
     payable
    1.17
     可
    1.16
     Runnable
    1.16
    的可
    1.14
    Activations Density 0.097%

    No Known Activations