© 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. 35387
    Prev
    Next
    INDEX
    Explanations

    comparison between things

    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
     poprzed
    0.45
     обы
    0.43
     обычной
    0.39
     предыду
    0.38
     previous
    0.38
     précédentes
    0.36
    谗
    0.35
     புகை
    0.34
     precedenti
    0.34
    MouseClicked
    0.34
    POSITIVE LOGITS
     줄
    0.41
    estis
    0.36
     laugh
    0.34
     Fields
    0.33
    აკ
    0.33
     विशाल
    0.33
     семья
    0.33
     અલગ
    0.33
    ulele
    0.33
     fiducia
    0.33
    Activations Density 0.018%

    No Known Activations