© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176445
    Prev
    Next
    INDEX
    Explanations

    average [measurement/attribute]

    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_20_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
    isierung
    0.48
    Approval
    0.48
    呀
    0.47
    approval
    0.46
     approval
    0.46
    fulness
    0.44
    ظر
    0.44
    ::
    0.43
    ificaciones
    0.43
    ustration
    0.43
    POSITIVE LOGITS
     surgi
    0.47
    离开
    0.46
    คาเดมี
    0.45
    ޅ
    0.44
     deixando
    0.44
     Arteta
    0.43
     कुटुंबा
    0.42
    Bingo
    0.41
    Mard
    0.41
    Чтобы
    0.40
    Activations Density 0.002%

    No Known Activations