© 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. 214461
    Prev
    Next
    INDEX
    Explanations

    public spaces

    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
    線
    1.77
    线
    1.63
    线的
    1.42
    線の
    1.41
     line
    1.30
    Line
    1.27
    線を
    1.27
     Line
    1.25
     線
    1.18
     线
    1.15
    POSITIVE LOGITS
    プラ
    0.53
     پلا
    0.49
     Plaza
    0.48
     salón
    0.45
    サロン
    0.44
     प्ला
    0.43
    스테
    0.42
    이터
    0.42
    ステ
    0.41
    opia
    0.41
    Activations Density 0.012%

    No Known Activations