© 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. 42655
    Prev
    Next
    INDEX
    Explanations

    `<env_name>` or `<config_value>`

    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
    し
    0.96
    ል።
    0.69
     आंकड़े
    0.65
    。
    0.64
    ες
    0.64
    िका
    0.64
    紹介
    0.63
    ਨ
    0.63
    底层
    0.61
    ም።
    0.61
    POSITIVE LOGITS
    '
    0.86
    0
    0.75
    <0x80>
    0.71
    '،
    0.69
    را
    0.64
     frå
    0.63
    "،
    0.61
    ak
    0.61
    nir
    0.59
    ld
    0.58
    Activations Density 0.001%

    No Known Activations