© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206796
    Prev
    Next
    INDEX
    Explanations

    container of items

    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_20_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
    unavailable
    0.36
    ཤ
    0.36
     revamped
    0.34
     pecuniary
    0.34
    abhavo
    0.34
    serif
    0.33
    𝓬
    0.33
     histidine
    0.33
     disrupted
    0.32
     misunderstood
    0.32
    POSITIVE LOGITS
    ology
    0.35
    endo
    0.34
     responde
    0.33
     अड्डा
    0.33
     VER
    0.32
     chica
    0.32
    vra
    0.32
    ierenden
    0.32
    emy
    0.32
     '/
    0.32
    Activations Density 0.000%

    No Known Activations