© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180266
    Prev
    Next
    INDEX
    Explanations

    cardinal directions in geography

    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_24_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
    djang
    0.40
    шал
    0.40
    viat
    0.40
    ausible
    0.37
    ieuse
    0.37
    Dutch
    0.37
    шает
    0.37
    菒
    0.36
    attutto
    0.36
    ग्रामीण
    0.36
    POSITIVE LOGITS
     văn
    0.38
     bertanggung
    0.37
    bollah
    0.36
     continuare
    0.36
     bunkers
    0.36
     Kopp
    0.35
    ritos
    0.35
     거고
    0.35
    సూరు
    0.34
     bunker
    0.34
    Activations Density 0.001%

    No Known Activations