© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12639
    Prev
    Next
    INDEX
    Explanations

    practical for

    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
     ISSN
    0.19
     pou
    0.17
    弓
    0.17
     vamp
    0.17
    avra
    0.17
    ↵
    0.16
     Insc
    0.15
     pousser
    0.15
     Pulitzer
    0.15
     foss
    0.15
    POSITIVE LOGITS
    ki
    0.24
    kt
    0.20
    ka
    0.20
    -”
    0.20
    ts
    0.19
    ks
    0.19
    ],”
    0.19
    are
    0.19
     garis
    0.18
    na
    0.18
    Activations Density 0.008%

    No Known Activations