© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103159
    Prev
    Next
    INDEX
    Explanations

    translation task requests

    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_1_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
    L
    1.52
    ר
    1.27
    は
    1.17
    C
    1.16
    M
    1.16
     \
    1.13
    া
    1.13
    다
    1.12
    B
    1.02
    ক
    1.02
    POSITIVE LOGITS
    st
    0.99
    ige
    0.91
     οποίο
    0.88
    ians
    0.87
    ன்
    0.85
    setter
    0.80
    ू
    0.80
    mith
    0.79
    chten
    0.77
    ifica
    0.76
    Activations Density 0.001%

    No Known Activations