© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209801
    Prev
    Next
    INDEX
    Explanations

    Anatolian | Turkish | rejection | experiences

    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_20_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
    rape
    0.46
    rakech
    0.46
    fY
    0.45
    inguished
    0.44
    ᐸ
    0.44
    ₽
    0.44
    腎
    0.44
    ſed
    0.43
     جنيه
    0.43
     insults
    0.42
    POSITIVE LOGITS
     ws
    0.52
     Wax
    0.48
     selain
    0.47
     Oasis
    0.47
     শ্র
    0.45
    Wax
    0.45
     asa
    0.45
     B
    0.44
     Bee
    0.44
     scattered
    0.44
    Activations Density 0.000%

    No Known Activations