© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99338
    Prev
    Next
    INDEX
    Explanations

    various ways

    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_16_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
    {
    0.52
     ment
    0.49
    utions
    0.48
    是
    0.48
    the
    0.47
    罗
    0.46
     si
    0.46
     the
    0.45
    ússia
    0.45
     donne
    0.45
    POSITIVE LOGITS
    𝗸
    0.57
     ಯಾವ
    0.56
     катастро
    0.52
     ಕಾಣ
    0.52
     churning
    0.52
     एच
    0.51
    }^{(\
    0.50
     COST
    0.50
     GER
    0.49
     ह
    0.49
    Activations Density 0.000%

    No Known Activations