© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3250
    Prev
    Next
    INDEX
    Explanations

    code blocks with indices or lengths

    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_40_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
    assignmentItems
    0.16
    Particles
    0.15
    hundred
    0.14
     centena
    0.14
    ijt
    0.14
    嶽
    0.14
    eight
    0.13
     Particles
    0.13
     tenfold
    0.13
    parad
    0.13
    POSITIVE LOGITS
    ♕
    0.15
    ….
    0.14
     sogar
    0.14
     disagreed
    0.14
     هایی
    0.13
     pave
    0.13
     ansch
    0.13
     slow
    0.13
     zelfs
    0.13
     postulated
    0.13
    Activations Density 0.085%

    No Known Activations