© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19152
    Prev
    Next
    INDEX
    Explanations

    how can / how is / how to / how does

    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_15_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
    стные
    0.30
    για
    0.29
    чка
    0.26
    чных
    0.26
    త్ప
    0.26
    ﹕
    0.26
    ventud
    0.26
     compañías
    0.25
    лизация
    0.25
    вия
    0.25
    POSITIVE LOGITS
     p
    0.28
     wants
    0.26
    ding
    0.26
    represents
    0.25
     sign
    0.24
     paternity
    0.24
     where
    0.24
    ?),
    0.24
     k
    0.24
     why
    0.24
    Activations Density 0.043%

    No Known Activations