© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22493
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     waarmee
    0.39
     geweest
    0.37
     sein
    0.35
     odl
    0.35
    тавли
    0.34
     மாய
    0.33
    𝒾
    0.33
    生まれた
    0.33
     कहां
    0.31
    ளான
    0.31
    POSITIVE LOGITS
    from
    3.08
     from
    2.94
    จาก
    2.53
    从
    2.50
     từ
    2.39
     från
    2.39
     FROM
    2.34
     फ्रॉम
    2.31
    從
    2.30
    From
    2.27
    Activations Density 0.135%

    No Known Activations