© 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. 76372
    Prev
    Next
    INDEX
    Explanations

    ez

    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
    UNDER
    0.32
    пто
    0.32
     अंडर
    0.32
     UNDER
    0.31
     علاقوں
    0.30
     انگل
    0.30
    楢
    0.30
     Ezek
    0.30
     Under
    0.29
    ᥣ
    0.29
    POSITIVE LOGITS
     se
    0.41
     sich
    0.41
     it
    0.37
     zich
    0.36
     się
    0.35
     इसे
    0.35
     ensuite
    0.33
     ne
    0.32
     particulier
    0.32
     themselves
    0.31
    Activations Density 0.000%

    No Known Activations