© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230744
    Prev
    Next
    INDEX
    Explanations

    regarding or concerning

    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_6_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
    '
    1.26
    ного
    1.12
     that
    1.01
    .
    1.00
    ל
    0.98
    ם
    0.94
    ную
    0.93
    ו
    0.93
    दार
    0.93
    า
    0.92
    POSITIVE LOGITS
    0
    1.43
    O
    1.22
    ne
    1.20
    )،
    1.18
    ins
    1.13
    ０
    1.13
    s
    1.12
    ،
    1.09
    ),
    1.06
    ០
    1.04
    Activations Density 0.002%

    No Known Activations