© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158758
    Prev
    Next
    INDEX
    Explanations

    spreadsheet related file types

    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
    ك
    1.96
    p
    1.80
    can
    1.48
    ch
    1.39
    ac
    1.30
    ete
    1.28
    ta
    1.24
    f
    1.24
    out
    1.22
    ren
    1.22
    POSITIVE LOGITS
    ৫
    1.64
    습니다
    1.39
    ции
    1.31
    ется
    1.13
    ==
    1.12
    ५
    1.10
    вся
    1.09
    ))
    1.08
    нения
    1.07
     zei
    1.05
    Activations Density 0.001%

    No Known Activations