© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236309
    Prev
    Next
    INDEX
    Explanations

    strengths

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Effective
    0.42
     kuten
    0.41
     like
    0.40
     instituted
    0.39
    Effective
    0.37
     adjudicated
    0.37
     poput
    0.37
    像
    0.36
     سلو
    0.36
     scrutinized
    0.36
    POSITIVE LOGITS
    咔
    0.47
    倛
    0.43
    の方法
    0.41
    Πα
    0.39
    ของการ
    0.38
     proble
    0.38
     problema
    0.38
    ጣጠ
    0.38
    prob
    0.37
    ましい
    0.36
    Activations Density 0.001%

    No Known Activations