© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31893
    Prev
    Next
    INDEX
    Explanations

    lucky numbers and phrases

    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_40_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
     التأ
    0.40
    楸
    0.39
    形势
    0.39
    טה
    0.38
    谱
    0.38
     pomp
    0.36
     honourable
    0.36
    遵循
    0.36
     reprises
    0.36
    ﻄ
    0.35
    POSITIVE LOGITS
    rafpunkte
    0.38
    tolist
    0.37
     carbonic
    0.37
    တွ
    0.37
     capitalist
    0.36
    ಟ್ರ
    0.36
     UnwrapRef
    0.36
     Ralf
    0.36
     Swallow
    0.36
     Flores
    0.35
    Activations Density 0.001%

    No Known Activations