© 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
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 44082
    Prev
    Next
    INDEX
    Explanations

    code blocks ending with } }

    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_22_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
     อะไร
    0.25
    ]+")
    0.25
    ).
    0.24
    )])
    0.24
     خطاب
    0.23
     கொடுத்து
    0.23
     котором
    0.23
     Такой
    0.23
    ]".
    0.22
    内置
    0.22
    POSITIVE LOGITS
    ਦਰ
    0.25
     favoring
    0.24
     considering
    0.24
    ک
    0.24
     being
    0.23
     advantage
    0.23
     affection
    0.23
     thé
    0.22
     combating
    0.22
     favors
    0.22
    Activations Density 0.005%

    No Known Activations