© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54016
    Prev
    Next
    INDEX
    Explanations

    too much

    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_31_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
     latitudes
    0.37
     latitude
    0.35
    ceded
    0.35
     ასევე
    0.35
    桉
    0.35
     HSC
    0.33
    платно
    0.33
    囟
    0.32
    눗
    0.32
     پاب
    0.32
    POSITIVE LOGITS
    ganggu
    0.42
    不需要
    0.38
    されない
    0.37
    すぎる
    0.36
     cárcel
    0.36
    不要
    0.36
     נישט
    0.35
    Greet
    0.35
     забы
    0.35
     ठो
    0.35
    Activations Density 0.000%

    No Known Activations