© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79149
    Prev
    Next
    INDEX
    Explanations

    M0

    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_31_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
    atoi
    0.28
    ждает
    0.26
    藏
    0.26
     television
    0.25
    旅
    0.25
    ridine
    0.25
    テレビ
    0.24
     travels
    0.24
    アルバ
    0.24
    話題
    0.24
    POSITIVE LOGITS
    弈
    0.29
     crescita
    0.28
     arquivos
    0.28
    锲
    0.28
     URANIUM
    0.27
     exf
    0.27
    넬
    0.27
    ὔ
    0.27
     выступ
    0.26
    会被
    0.26
    Activations Density 0.000%

    No Known Activations