© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82642
    Prev
    Next
    INDEX
    Explanations

    name

    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_53_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
     WM
    0.48
    WM
    0.47
    WMN
    0.44
     WJ
    0.42
     NKG
    0.42
    WL
    0.41
    Ｗ
    0.41
     Wir
    0.40
     Wii
    0.40
    WN
    0.40
    POSITIVE LOGITS
    വധി
    0.40
    fi
    0.38
    expect
    0.37
    riam
    0.37
    выми
    0.36
     Вя
    0.35
     ভ
    0.35
    utives
    0.35
    ቪ
    0.35
     dihap
    0.34
    Activations Density 0.001%

    No Known Activations