© 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. 54018
    Prev
    Next
    INDEX
    Explanations

    model response

    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
    Би
    0.40
     ).
    0.38
    ımın
    0.38
    și
    0.37
    এল
    0.37
    Transport
    0.36
     ))
    0.36
     ));
    0.36
    噬
    0.36
     eld
    0.35
    POSITIVE LOGITS
     cát
    0.39
    惶
    0.38
     pron
    0.37
    hofer
    0.36
    трим
    0.35
     ఒక్క
    0.34
     ഓരോ
    0.34
    dX
    0.33
     доля
    0.33
     проводить
    0.32
    Activations Density 0.000%

    No Known Activations