© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108367
    Prev
    Next
    INDEX
    Explanations

    ascertain, determine, verify

    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_2_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
    v
    1.42
    न
    1.37
    tt
    1.34
    p
    1.32
    ن
    1.32
    st
    1.31
    dd
    1.30
    ttt
    1.24
    ts
    1.23
    ку
    1.23
    POSITIVE LOGITS
    is
    1.38
    는
    1.16
     The
    1.13
    ти
    1.13
    ид
    1.13
    ৯
    1.13
    т
    1.12
    ння
    1.11
    ер
    1.08
    ными
    1.07
    Activations Density 0.000%

    No Known Activations