© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31740
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    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_50_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
    anam
    0.62
    నం
    0.53
    hanam
    0.51
    னம்
    0.48
     HANA
    0.43
    ಣ
    0.42
     Horizontal
    0.42
    নং
    0.41
    ணம்
    0.41
    ધન
    0.41
    POSITIVE LOGITS
    ہا
    0.42
    asar
    0.41
    isam
    0.41
    ோது
    0.41
    வதற்கு
    0.38
    ﮨ
    0.38
    ༔
    0.38
    र्देश
    0.38
    ൂടെ
    0.37
    瘁
    0.37
    Activations Density 0.001%

    No Known Activations