© 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. 62201
    Prev
    Next
    INDEX
    Explanations

    using something regularly

    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
    er
    1.59
    en
    1.55
    d
    1.51
    ad
    1.42
    t
    1.39
    ana
    1.34
    Q
    1.21
    us
    1.13
    in
    1.12
    de
    1.12
    POSITIVE LOGITS
    که
    1.58
     که
    1.54
    기는
    1.54
    נו
    1.53
    ג
    1.53
    פ
    1.47
    کت
    1.38
    کام
    1.34
    리
    1.34
    یم
    1.31
    Activations Density 0.001%

    No Known Activations