© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 213224
    Prev
    Next
    INDEX
    Explanations

    anonymous classes or object instances

    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_16_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
    ad
    0.57
    es
    0.55
    et
    0.53
    ]
    0.52
     admissibility
    0.51
    eses
    0.50
    at
    0.48
     confrontations
    0.47
     delays
    0.47
     confrontation
    0.47
    POSITIVE LOGITS
    ทั้งหมด
    0.55
    ریک
    0.53
    راق
    0.52
    жению
    0.52
    觴
    0.52
     منظر
    0.49
     väik
    0.49
    rabbit
    0.48
    )}(
    0.47
     nhỏ
    0.47
    Activations Density 0.001%

    No Known Activations