© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111155
    Prev
    Next
    INDEX
    Explanations

    import React from 'react'

    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_2_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
    ט
    1.11
     but
    0.93
     with
    0.88
     t
    0.88
     tapestry
    0.86
     and
    0.85
     U
    0.85
     water
    0.85
     from
    0.84
    רי
    0.84
    POSITIVE LOGITS
    ك
    1.22
    ↵↵
    1.14
    dı
    1.03
    LE
    1.01
    kan
    1.01
    O
    1.01
    the
    1.00
    乎
    0.98
    IN
    0.97
    ка
    0.96
    Activations Density 0.005%

    No Known Activations