© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217172
    Prev
    Next
    INDEX
    Explanations

    counting elements in texts

    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_16_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
    グ
    0.46
    бли
    0.44
    нти
    0.42
    ạp
    0.42
    ärg
    0.41
    गुड
    0.41
    inker
    0.40
     го
    0.40
    ả
    0.39
    лена
    0.39
    POSITIVE LOGITS
     agonist
    0.52
     Qxa
    0.51
     samano
    0.50
     vowels
    0.50
     cerc
    0.50
     Qaeda
    0.50
     demeanor
    0.49
     जटिल
    0.49
     vVertex
    0.49
     tortue
    0.48
    Activations Density 0.000%

    No Known Activations