© 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. 242681
    Prev
    Next
    INDEX
    Explanations

    im...ura / im...:** / rim...Riverside

    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
    태
    0.40
    㐫
    0.39
    illed
    0.38
    栤
    0.38
     sempat
    0.37
    disc
    0.36
     infrast
    0.36
    தான
    0.36
    opera
    0.35
    森
    0.35
    POSITIVE LOGITS
     darken
    0.42
     Cavan
    0.38
     Kav
    0.37
     প্রাধ
    0.36
     учет
    0.35
     phiếu
    0.35
    bursement
    0.35
     práv
    0.35
     Immer
    0.35
     Vendors
    0.35
    Activations Density 0.010%

    No Known Activations