© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140868
    Prev
    Next
    INDEX
    Explanations

    gaming and online communities

    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
     elk
    0.41
     Kähler
    0.38
     Mét
    0.38
    𒉡
    0.37
    ätten
    0.36
     psig
    0.35
    wegen
    0.35
    ilen
    0.34
     כך
    0.34
    敉
    0.34
    POSITIVE LOGITS
     Burd
    0.39
    Special
    0.37
    〈
    0.37
    ﴾
    0.37
    嬗
    0.36
    ˋ
    0.36
    Zaw
    0.36
    Traditional
    0.35
    Entertainment
    0.35
     Cos
    0.35
    Activations Density 0.000%

    No Known Activations