© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97192
    Prev
    Next
    INDEX
    Explanations

    and welcome greetings

    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_14_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
     splitting
    0.48
    ما
    0.42
    at
    0.39
    Agent
    0.39
    телно
    0.38
    赟
    0.38
    دي
    0.38
     splits
    0.38
     tables
    0.37
    Dead
    0.37
    POSITIVE LOGITS
     für
    0.51
    椃
    0.45
     वापरा
    0.44
    𒊏
    0.44
     historie
    0.43
    哣
    0.41
    gani
    0.41
    *,
    0.40
    gana
    0.40
     মনোভাব
    0.39
    Activations Density 0.001%

    No Known Activations