© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104726
    Prev
    Next
    INDEX
    Explanations

    feeling supported

    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
     noastră
    1.17
    ும்
    1.16
    т
    1.11
    га
    1.06
    ală
    1.03
    gli
    1.02
    ι
    1.02
     máu
    0.98
    תן
    0.97
    るので
    0.97
    POSITIVE LOGITS
    1
    1.33
    c
    1.18
    ot
    1.15
    ra
    1.09
    ad
    1.02
    te
    0.98
    s
    0.96
    ne
    0.93
     at
    0.88
    ap
    0.86
    Activations Density 0.002%

    No Known Activations