© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27293
    Prev
    Next
    INDEX
    Explanations

    go or went to

    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_40_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
    Went
    0.55
    went
    0.50
     went
    0.45
     идти
    0.43
     gå
    0.43
    ไป
    0.42
    去
    0.42
     Went
    0.42
     goin
    0.41
     pergi
    0.41
    POSITIVE LOGITS
     dresses
    0.42
    籃
    0.40
     বাল
    0.38
     attendants
    0.38
     dress
    0.36
     joggers
    0.36
    cił
    0.36
     espress
    0.36
    டுதல்
    0.36
     footballers
    0.36
    Activations Density 0.004%

    No Known Activations