© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199087
    Prev
    Next
    INDEX
    Explanations

    remembering past events

    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_50_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
     ثلاث
    0.42
    adio
    0.41
     zwei
    0.40
    三個
    0.38
     drei
    0.38
     ಎಷ್ಟು
    0.38
    尅
    0.38
     তিনটি
    0.38
     three
    0.37
     두
    0.37
    POSITIVE LOGITS
     Cornish
    0.44
     Day
    0.39
    èt
    0.39
     Ted
    0.39
     Landkreis
    0.39
     denotes
    0.38
     airfield
    0.38
     Дмитрий
    0.38
    CJK
    0.37
     Wentworth
    0.37
    Activations Density 0.000%

    No Known Activations