© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62612
    Prev
    Next
    INDEX
    Explanations

    German context

    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_59_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
     ఉంటు
    0.41
    ંગ
    0.38
    魄
    0.36
    何
    0.36
    rän
    0.36
    gangen
    0.35
    厚生
    0.35
    WUE
    0.34
    Kale
    0.34
    מ
    0.34
    POSITIVE LOGITS
     سو
    0.75
     سوا
    0.60
     Su
    0.56
     су
    0.48
     su
    0.46
     stra
    0.46
    سو
    0.46
    su
    0.42
     Ser
    0.40
     Miss
    0.40
    Activations Density 0.006%

    No Known Activations