© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203729
    Prev
    Next
    INDEX
    Explanations

    remembering

    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
    т
    1.06
    ро
    0.94
    п
    0.93
    </h3>
    0.85
    ι
    0.85
    ร
    0.84
    и
    0.82
     rearing
    0.80
     musi
    0.80
    they
    0.78
    POSITIVE LOGITS
    ق
    1.34
    ن
    1.20
    }.
    1.14
    SI
    1.10
    TE
    1.09
    N
    1.09
    س
    1.09
    TS
    1.06
    Có
    1.04
     a
    1.02
    Activations Density 0.001%

    No Known Activations