© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154910
    Prev
    Next
    INDEX
    Explanations

    a

    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
    anding
    0.38
    かと
    0.36
    light
    0.35
     നിര്‍
    0.35
    爿
    0.35
    ﺶ
    0.35
     PROM
    0.34
    noi
    0.34
    гар
    0.34
    PLC
    0.34
    POSITIVE LOGITS
    𝘾
    0.42
     Wellington
    0.41
     filesize
    0.39
    วัง
    0.39
     Oceans
    0.38
    Eso
    0.38
     antise
    0.38
    łym
    0.38
    эффици
    0.37
     BOB
    0.37
    Activations Density 0.002%

    No Known Activations