© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116445
    Prev
    Next
    INDEX
    Explanations

    numerical word problems

    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_27_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
     Hole
    0.37
     hole
    0.36
     dietitian
    0.36
     CDN
    0.35
     MIUI
    0.35
     strait
    0.35
     lurking
    0.35
    （
    0.35
     exercises
    0.34
     standpoint
    0.34
    POSITIVE LOGITS
     innocence
    0.39
     পারব
    0.38
    ล็อก
    0.38
     isother
    0.38
     јуну
    0.38
     podríamos
    0.38
    Logan
    0.37
    returnValues
    0.37
    បរ
    0.37
    Athens
    0.37
    Activations Density 0.002%

    No Known Activations