© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62220
    Prev
    Next
    INDEX
    Explanations

    tackling, Googling, struggling

    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_2_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
     in
    1.38
    اً
    1.15
    از
    1.13
    के
    1.04
    با
    1.03
    رو
    1.02
    P
    1.02
    MT
    1.02
    きた
    1.01
    TI
    0.99
    POSITIVE LOGITS
    ин
    1.20
    á
    1.17
    <0x80>
    1.08
    𝙣
    1.08
    ד
    1.04
    ти
    1.03
    کي
    1.02
    
    1.00
    ሳሪያ
    0.98
    ланти
    0.98
    Activations Density 0.001%

    No Known Activations