© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243399
    Prev
    Next
    INDEX
    Explanations

    you have done or we've done

    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_40_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
     impressive
    0.45
    মাপ
    0.43
     U
    0.42
     fri
    0.40
     feat
    0.40
     sport
    0.38
     gel
    0.38
     feats
    0.38
     pra
    0.38
     freund
    0.37
    POSITIVE LOGITS
    ಡೆಯ
    0.41
    껀
    0.38
     Needed
    0.38
    かは
    0.37
     InputListener
    0.36
    Thing
    0.36
     COLORS
    0.36
    ेश्च
    0.35
     entwickeln
    0.35
     dibutuhkan
    0.35
    Activations Density 0.005%

    No Known Activations