© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229564
    Prev
    Next
    INDEX
    Explanations

    Hindi statements

    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_57_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
    se
    0.46
    rawy
    0.45
     se
    0.43
     해서
    0.40
    <0xE3>
    0.40
    Se
    0.39
    anto
    0.38
    ulture
    0.38
     wa
    0.38
    해서
    0.37
    POSITIVE LOGITS
     tüm
    0.45
     всі
    0.44
     вся
    0.43
     vš
    0.42
    全都
    0.40
     усі
    0.39
     seluruh
    0.39
    鄞
    0.39
     PREC
    0.39
    Kent
    0.37
    Activations Density 0.000%

    No Known Activations