© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37899
    Prev
    Next
    INDEX
    Explanations

    control tokens

    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
    }},
    0.38
     বেঁচে
    0.35
    }}:=\
    0.33
     بالنسبة
    0.32
    そして
    0.31
    ']],
    0.31
    ENEMY
    0.31
    <unused60>
    0.31
    अधिक
    0.31
    ాల్సిన
    0.31
    POSITIVE LOGITS
    𝑔
    0.42
    ﻉ
    0.41
    𝗴
    0.40
    𝘆
    0.39
     ;\
    0.39
    Ų
    0.38
    ⾃
    0.38
     ர
    0.37
     अनुमति
    0.37
    тика
    0.37
    Activations Density 0.899%

    No Known Activations