© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194448
    Prev
    Next
    INDEX
    Explanations

    pressing Enter

    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_4_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
    '
    0.27
    在
    0.19
    of
    0.18
    ේ
    0.18
    '></
    0.18
    >
    0.17
    '।
    0.17
    ).
    0.17
    ৮
    0.17
    قال
    0.16
    POSITIVE LOGITS
     you
    0.27
     for
    0.26
     your
    0.25
     from
    0.24
    ik
    0.24
     with
    0.23
    I
    0.22
     about
    0.21
     who
    0.21
    ie
    0.20
    Activations Density 0.062%

    No Known Activations