© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171159
    Prev
    Next
    INDEX
    Explanations

    list item delimiters or separators

    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_20_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
     ख़
    0.36
     rumored
    0.35
     harbors
    0.35
     ผม
    0.33
    rangle
    0.33
    ]
    0.33
     rumors
    0.32
    ผม
    0.32
    It
    0.32
    finalize
    0.31
    POSITIVE LOGITS
     jeder
    0.34
    ન્ટે
    0.34
     each
    0.34
    が集
    0.32
    दर्शन
    0.32
    鳩
    0.32
     Japanese
    0.31
     jährlich
    0.31
     каждая
    0.31
    observ
    0.31
    Activations Density 0.002%

    No Known Activations