© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107679
    Prev
    Next
    INDEX
    Explanations

    Spanish words

    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_1_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
    cs
    1.13
    ke
    1.05
    chen
    1.04
    cer
    0.96
    ars
    0.94
    *
    0.94
    gt
    0.93
    cy
    0.93
    ila
    0.91
    AD
    0.91
    POSITIVE LOGITS
    ной
    1.34
    다음
    1.32
    다는
    1.25
    드의
    1.21
    스를
    1.20
    et
    1.17
    م
    1.16
    میں
    1.13
    رک
    1.13
    ம்
    1.13
    Activations Density 0.002%

    No Known Activations