© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171900
    Prev
    Next
    INDEX
    Explanations

    Q followed by a quarter

    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_20_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
    K
    0.42
    ро
    0.40
    ियंस
    0.39
    Laura
    0.39
    ros
    0.38
    ک
    0.38
    ]}
    0.37
    க
    0.37
    Der
    0.37
    ябрь
    0.36
    POSITIVE LOGITS
    嶈
    0.43
     Byzant
    0.42
     Foundry
    0.42
     Bulb
    0.42
     Apica
    0.41
     शीजान
    0.41
     Transformer
    0.41
     Terminator
    0.41
     tratados
    0.40
     লিপিবদ্ধ
    0.40
    Activations Density 0.001%

    No Known Activations