© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201874
    Prev
    Next
    INDEX
    Explanations

    airport codes London

    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_6_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
     recib
    1.02
    )
    1.01
    </h4>
    0.98
    </strong>
    0.94
    ﻥ
    0.94
    লে
    0.92
     cataly
    0.91
     can
    0.88
    ν
    0.88
    ﻜ
    0.85
    POSITIVE LOGITS
    ى
    1.39
    z
    1.23
    يد
    1.12
    IS
    1.11
    В
    1.11
    ale
    1.09
    on
    1.09
    j
    1.09
    ോ
    1.09
    E
    1.07
    Activations Density 0.001%

    No Known Activations