© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132654
    Prev
    Next
    INDEX
    Explanations

    doorknobs

    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_1_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
    ri
    1.59
    ro
    1.30
    1.30
    s
    1.27
    r
    1.26
    ين
    1.25
    न
    1.23
    ru
    1.22
    ss
    1.22
    st
    1.20
    POSITIVE LOGITS
    ið
    1.02
     fathom
    1.02
    이가
    0.99
    ᆷ
    0.99
    ﻲ
    0.98
    нер
    0.97
    нта
    0.97
    在于
    0.97
    atka
    0.96
    ﻚ
    0.96
    Activations Density 0.000%

    No Known Activations