© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250774
    Prev
    Next
    INDEX
    Explanations

    's

    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_56_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
     left
    1.21
    left
    1.00
     LEFT
    0.98
    左
    0.93
     izquierda
    0.91
     Left
    0.89
    LEFT
    0.84
    Left
    0.84
     बाएं
    0.78
     বাম
    0.78
    POSITIVE LOGITS
     کھیلوں
    0.40
    worth
    0.38
    Ϻ
    0.38
    urved
    0.37
     Advertising
    0.37
    ruiter
    0.37
    ward
    0.37
    Trab
    0.36
    buscador
    0.36
     вышел
    0.36
    Activations Density 0.004%

    No Known Activations