© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81909
    Prev
    Next
    INDEX
    Explanations

    ,

    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_29_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
     എന്നിവ
    0.56
     etc
    0.55
     등으로
    0.54
    等的
    0.53
     тощо
    0.53
     എന്നീ
    0.52
    等等
    0.51
     等
    0.50
     등을
    0.49
    etc
    0.49
    POSITIVE LOGITS
     pairwise
    0.37
    })$,
    0.36
    bie
    0.34
    无论是
    0.34
     prvo
    0.34
     verticals
    0.34
     निकालते
    0.34
     '
    0.33
    cl
    0.33
     зазна
    0.33
    Activations Density 0.026%

    No Known Activations