© 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. 141829
    Prev
    Next
    INDEX
    Explanations

    0

    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
     нуле
    0.51
    henge
    0.45
    ینڈ
    0.41
     Gründen
    0.39
    ntl
    0.39
     (>
    0.39
    শংস
    0.39
     ರೀ
    0.38
    قيقة
    0.38
     wanting
    0.37
    POSITIVE LOGITS
    disp
    0.38
     undert
    0.37
    disamb
    0.36
     Corre
    0.35
     चाल
    0.35
     쿠
    0.35
    tor
    0.35
     days
    0.35
    identity
    0.35
    Slow
    0.35
    Activations Density 0.004%

    No Known Activations