© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39527
    Prev
    Next
    INDEX
    Explanations

    r

    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_57_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
    ിയെ
    0.56
    ִ
    0.55
    ിയും
    0.54
    ీ
    0.54
    ੀ
    0.54
    ிகளை
    0.52
    ִי
    0.51
    ിയുടെ
    0.50
    િ
    0.50
    ijuana
    0.49
    POSITIVE LOGITS
    а
    0.91
    𝗮
    0.89
    ᴀ
    0.87
    ａ
    0.85
    af
    0.84
    ah
    0.81
    𝐚
    0.81
    ɑ
    0.80
    α
    0.79
    𝙖
    0.79
    Activations Density 0.025%

    No Known Activations