© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89179
    Prev
    Next
    INDEX
    Explanations

    Italian suffixes

    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_60_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
    ционер
    0.49
     il
    0.48
    чнай
    0.48
    𝙛
    0.45
    𝐜
    0.45
     ajustes
    0.45
    𝙘
    0.45
    ד
    0.44
    ﺙ
    0.44
    𝘿
    0.44
    POSITIVE LOGITS
    ro
    1.17
    rich
    1.02
    ri
    0.89
    ron
    0.82
    RO
    0.76
    Rich
    0.74
    ria
    0.73
    RICH
    0.72
    roni
    0.71
    rom
    0.70
    Activations Density 0.000%

    No Known Activations