© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14384
    Prev
    Next
    INDEX
    Explanations

    outdoor structures and seating

    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_13_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
     महिला
    0.39
     pigments
    0.38
     францу
    0.38
     stripos
    0.37
     крови
    0.37
     pregnancies
    0.36
     personer
    0.36
    y
    0.36
     producent
    0.36
     wanita
    0.36
    POSITIVE LOGITS
    ամ
    0.35
    ahun
    0.35
    emos
    0.35
    AllWindows
    0.34
    Lemma
    0.34
    ველ
    0.34
    iley
    0.33
    Very
    0.33
     הם
    0.33
    archivo
    0.33
    Activations Density 0.038%

    No Known Activations