© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259462
    Prev
    Next
    INDEX
    Explanations

    team capabilities

    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
    трі
    0.43
    this
    0.42
    ｏ
    0.42
    ～
    0.41
    ങ്ങളിലും
    0.40
    mén
    0.40
     również
    0.39
    і
    0.39
    ѕ
    0.39
     l
    0.39
    POSITIVE LOGITS
    RIK
    0.49
    insuku
    0.42
    DAAR
    0.42
    ERICA
    0.41
    agaan
    0.41
    Folders
    0.41
     богат
    0.40
    ཏ
    0.39
    騷
    0.39
    ARIOS
    0.39
    Activations Density 0.000%

    No Known Activations