© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260792
    Prev
    Next
    INDEX
    Explanations

    hairdryer or hairline

    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_5_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
    1.45
    س
    1.30
    ль
    1.16
    ا
    1.15
    ด
    1.15
    로
    1.13
    み
    1.13
    ス
    1.12
    한
    1.10
    ס
    1.05
    POSITIVE LOGITS
    ',$
    1.20
     Dyed
    1.13
    𝟏
    1.09
    <unused525>
    1.07
    ()]
    1.06
    ’;
    1.06
    νει
    1.06
    IsIn
    1.06
     плану
    1.05
    ];//
    1.04
    Activations Density 0.000%

    No Known Activations