© 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
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132144
    Prev
    Next
    INDEX
    Explanations

    take/absorb

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     вересня
    0.45
    稱
    0.42
     сентября
    0.41
    রম
    0.41
    ivered
    0.40
     Mullen
    0.40
    дат
    0.39
     Levi
    0.38
     добро
    0.37
     نصب
    0.36
    POSITIVE LOGITS
    弃
    0.66
    取
    0.59
    棄
    0.58
     thú
    0.56
     taken
    0.48
     thụ
    0.44
    취
    0.44
    ouch
    0.44
     Taken
    0.43
    呼
    0.42
    Activations Density 0.000%

    No Known Activations