© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131495
    Prev
    Next
    INDEX
    Explanations

    VAEs learn latent space

    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_1_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
    _
    1.25
    (
    1.18
    é
    1.16
    of
    1.08
    ານ
    1.03
     esteja
    1.03
    ala
    1.02
     abbia
    1.01
    "
    1.01
     deverá
    1.00
    POSITIVE LOGITS
    ح
    1.05
    ین
    1.03
    un
    1.02
    র
    1.01
    ן
    0.98
    ע
    0.95
    एं
    0.91
    י
    0.89
     μία
    0.88
    5
    0.87
    Activations Density 0.000%

    No Known Activations