© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211652
    Prev
    Next
    INDEX
    Explanations

    samsara

    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
            
    1.34
        
    1.26
    UT
    1.25
    O
    1.25
    ל
    1.18
     in
    1.13
    EL
    1.12
    a
    1.08
          
    1.07
    t
    1.07
    POSITIVE LOGITS
    த்தில்
    1.41
    ام
    1.34
    지
    1.29
    ку
    1.28
    िक
    1.24
    та
    1.24
    ہ
    1.20
    ای
    1.16
    is
    1.14
    𝚗
    1.13
    Activations Density 0.000%

    No Known Activations