© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43678
    Prev
    Next
    INDEX
    Explanations

    #!/bin/bash

    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_3_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
    1.15
    ক
    0.87
    س
    0.84
    к
    0.83
    ק
    0.81
    י
    0.77
    м
    0.74
     исто
    0.74
     materiál
    0.73
     дерева
    0.72
    POSITIVE LOGITS
    on
    1.13
    t
    0.95
    CG
    0.82
    oise
    0.79
    plemented
    0.71
    has
    0.69
    ar
    0.68
    et
    0.68
    aura
    0.68
    o
    0.68
    Activations Density 0.001%

    No Known Activations