© 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. 82462
    Prev
    Next
    INDEX
    Explanations

    Herr

    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
    れている
    0.40
     থাকিলেও
    0.39
    挺
    0.38
    shipping
    0.38
     throttling
    0.38
    ጵ
    0.37
     Ambris
    0.37
    ablus
    0.37
    ємо
    0.36
    ⊆
    0.36
    POSITIVE LOGITS
     Herr
    1.54
     Hers
    1.48
    Herr
    1.48
     hers
    1.42
     HER
    1.42
     herr
    1.42
    Hers
    1.41
    HER
    1.32
    herr
    1.23
    her
    1.21
    Activations Density 0.001%

    No Known Activations