© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230349
    Prev
    Next
    INDEX
    Explanations

    cloud-based services and platforms

    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_6_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
    s
    1.24
    ä
    1.14
    am
    1.04
    س
    1.01
     dioxide
    0.89
    e
    0.87
     salami
    0.85
    a
    0.85
     नती
    0.78
    é
    0.76
    POSITIVE LOGITS
    "
    0.98
    ﻱ
    0.86
    ר
    0.84
    ף
    0.81
    "",
    0.77
    "^
    0.76
    ppure
    0.76
    ল
    0.73
    ﺓ
    0.73
    נס
    0.73
    Activations Density 0.001%

    No Known Activations