© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167284
    Prev
    Next
    INDEX
    Explanations

    namely, meaning, or rather

    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_31_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
    ;$
    0.38
    它可以
    0.38
    彼は
    0.37
    佢
    0.37
     Они
    0.36
     তারা
    0.36
    itin
    0.35
     they
    0.35
    [];
    0.35
    ;(
    0.34
    POSITIVE LOGITS
     тобто
    0.50
    つまり
    0.45
     tedy
    0.44
     ovvero
    0.43
     וש
    0.42
     म्हणजेच
    0.42
     यानी
    0.42
    بھ
    0.40
     yani
    0.40
     অর্থাৎ
    0.39
    Activations Density 0.037%

    No Known Activations