© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11553
    Prev
    Next
    INDEX
    Explanations

    looking for besides

    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_13_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
     собственной
    0.27
     subordinates
    0.26
     without
    0.25
    }$.
    0.25
     zonder
    0.25
     bx
    0.25
     أعمال
    0.25
     throughout
    0.25
    ଈ
    0.25
    ਜ਼
    0.25
    POSITIVE LOGITS
    <0x0D>
    0.30
    eto
    0.22
    aría
    0.22
     alleviation
    0.22
     stately
    0.21
     jarring
    0.21
    atin
    0.21
    ান্তরে
    0.21
     cuadrado
    0.21
     wreath
    0.21
    Activations Density 0.015%

    No Known Activations