© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165504
    Prev
    Next
    INDEX
    Explanations

    south, southeast, southwest, northwest

    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_31_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
     நன்றாக
    0.42
     скло
    0.37
    ỷ
    0.37
    tey
    0.37
     contentView
    0.36
     primitive
    0.36
    adro
    0.36
     meadows
    0.35
     stev
    0.35
     Nox
    0.35
    POSITIVE LOGITS
     हेयर
    0.42
     চুল
    0.41
     pencil
    0.40
     Hair
    0.39
    💂
    0.39
    发
    0.38
     synth
    0.37
     nationwide
    0.37
     unpaid
    0.36
     kanssa
    0.36
    Activations Density 0.000%

    No Known Activations