© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206615
    Prev
    Next
    INDEX
    Explanations

    debit and credit entries

    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
     tová
    0.47
     quen
    0.45
    מש
    0.44
    BigAutoField
    0.43
     digunakan
    0.43
     المش
    0.42
    に着
    0.42
    ဦ
    0.41
     smel
    0.41
     contractName
    0.41
    POSITIVE LOGITS
    others
    0.48
    Others
    0.48
     दूसरों
    0.46
    ka
    0.45
    raf
    0.44
    vin
    0.44
    zz
    0.43
    visa
    0.43
    astaan
    0.43
    annes
    0.43
    Activations Density 0.001%

    No Known Activations