© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78809
    Prev
    Next
    INDEX
    Explanations

    involucrado

    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_0_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
    1.52
    ia
    1.26
     and
    1.19
    បាន
    1.16
    ை
    1.10
     Voices
    1.09
    ת
    1.06
    ᆸ
    1.06
    棪
    1.05
    ა
    1.04
    POSITIVE LOGITS
    m
    1.77
    ri
    1.76
    l
    1.74
    un
    1.52
    ren
    1.38
    кс
    1.34
    lk
    1.34
    te
    1.34
    den
    1.34
    tt
    1.33
    Activations Density 0.001%

    No Known Activations