© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261670
    Prev
    Next
    INDEX
    Explanations

    connecting concepts or listing items

    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_22_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
     titulares
    0.26
    ருங்கள்
    0.26
    ທ່ານ
    0.24
     completions
    0.24
    కున్న
    0.24
     shov
    0.24
     July
    0.24
    ූ
    0.24
     ο
    0.23
    irittura
    0.23
    POSITIVE LOGITS
     sebagainya
    0.27
    キシ
    0.25
    বাড়ি
    0.25
     nevoie
    0.25
     ట్ర
    0.25
    न्त्र
    0.24
    بيت
    0.24
     البيت
    0.24
    Downtown
    0.23
    ^{\
    0.23
    Activations Density 0.005%

    No Known Activations