© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248760
    Prev
    Next
    INDEX
    Explanations

    AI assistant

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     سلامه
    0.42
    ﻧ
    0.39
     პროგრამ
    0.38
    誢
    0.38
    சாய
    0.37
     Siamo
    0.36
     инфек
    0.36
    鿁
    0.36
     ребён
    0.35
    𝐽
    0.35
    POSITIVE LOGITS
     well
    0.46
     repeating
    0.40
     repeater
    0.39
     way
    0.39
     could
    0.38
    得到
    0.38
     long
    0.37
     plane
    0.37
    well
    0.37
     reflector
    0.37
    Activations Density 0.000%

    No Known Activations