© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 200940
    Prev
    Next
    INDEX
    Explanations

    film titles, characters, and regions

    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_12_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
    ֩
    0.58
    )~
    0.56
    )-
    0.55
     oxidizing
    0.54
    </h5>
    0.53
    ிலிருந்து
    0.52
    ﮟ
    0.52
     Samm
    0.50
    )』
    0.50
     alumn
    0.50
    POSITIVE LOGITS
     Z
    0.55
    Tape
    0.53
     کرا
    0.52
    pherds
    0.51
    1
    0.51
     z
    0.51
    헬
    0.50
    ":
    0.50
    ры
    0.50
    夜
    0.49
    Activations Density 0.000%

    No Known Activations