© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4371
    Prev
    Next
    INDEX
    Explanations

    python input() or print()

    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_40_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
     übertr
    0.41
     Verbre
    0.38
     mentally
    0.37
     дам
    0.36
     Usu
    0.35
     psychotherapy
    0.34
    ెంబ
    0.34
    <unused35>
    0.34
     जुड़
    0.34
     Dynamo
    0.34
    POSITIVE LOGITS
     input
    2.63
    input
    2.48
     Input
    2.45
    Input
    2.39
     INPUT
    2.02
    INPUT
    1.89
    入力
    1.82
    输入
    1.78
     inputs
    1.52
     입력
    1.51
    Activations Density 0.102%

    No Known Activations