© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59115
    Prev
    Next
    INDEX
    Explanations

    German "häufig"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ’
    1.03
    '
    0.93
     ſt
    0.92
    dı
    0.91
    ᆹ
    0.91
    d
    0.88
    dz
    0.87
    در
    0.86
    €™
    0.86
     These
    0.84
    POSITIVE LOGITS
    0
    1.17
    И
    1.16
    ing
    0.99
    j
    0.96
    ना
    0.95
     impasse
    0.92
    한
    0.91
    الی
    0.91
     kereta
    0.91
    udah
    0.89
    Activations Density 0.000%

    No Known Activations