© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124158
    Prev
    Next
    INDEX
    Explanations

    TPM or TPUs

    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_3_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
    speople
    0.82
    topology
    0.78
    sized
    0.71
    ਮ
    0.68
    異なる
    0.68
     پایین
    0.68
    screening
    0.68
    ட்ட
    0.67
    siswa
    0.67
    ла
    0.66
    POSITIVE LOGITS
     an
    0.88
     l
    0.81
     TPM
    0.74
    Β
    0.74
    et
    0.71
    ’
    0.70
    ل
    0.70
     de
    0.69
     \
    0.69
     Β
    0.68
    Activations Density 0.001%

    No Known Activations