© 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. 31401
    Prev
    Next
    INDEX
    Explanations

    place

    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
    <unused8>
    0.36
    凋
    0.35
    🇸
    0.34
     አስተ
    0.34
    kings
    0.34
    boiled
    0.33
    끄
    0.33
    )—
    0.32
    стры
    0.32
    )–
    0.32
    POSITIVE LOGITS
     Place
    2.81
    Place
    2.80
     place
    2.66
    place
    2.55
     PLACE
    2.48
    PLACE
    2.44
     places
    2.33
     Places
    2.33
    Places
    2.22
     lugar
    2.20
    Activations Density 0.232%

    No Known Activations