© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200807
    Prev
    Next
    INDEX
    Explanations

    EliteDesk 800 G1 touchscreen

    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_12_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
    бы
    0.43
    حدث
    0.42
    هر
    0.42
    绚
    0.42
    延长
    0.42
    வக
    0.41
    ক্রমন
    0.41
    莪
    0.41
    شتہ
    0.41
    ረጋ
    0.41
    POSITIVE LOGITS
     smoot
    0.46
     situações
    0.44
     overhe
    0.44
     डाउट
    0.43
     Smoothing
    0.42
     smach
    0.41
     Newtonian
    0.41
     PRE
    0.41
    eenth
    0.41
    roscopic
    0.40
    Activations Density 0.002%

    No Known Activations