© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33480
    Prev
    Next
    INDEX
    Explanations

    P

    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_50_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
    rp
    0.50
    <0x89>
    0.47
    KP
    0.47
    NP
    0.46
    P
    0.46
     KP
    0.45
     TP
    0.44
     RP
    0.44
    畤
    0.44
    TP
    0.43
    POSITIVE LOGITS
    රා
    0.45
    preventDefault
    0.40
     trả
    0.38
     hd
    0.38
     Vire
    0.38
    往
    0.38
    脛
    0.37
    ビネット
    0.37
    苔
    0.36
    Ｖ
    0.36
    Activations Density 0.005%

    No Known Activations