© 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. 210546
    Prev
    Next
    INDEX
    Explanations

    Good for

    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
     hend
    0.45
    ，
    0.44
     Mimi
    0.44
     pillar
    0.44
    дор
    0.43
     stake
    0.41
    」，
    0.41
    मनी
    0.41
    妃
    0.41
     inher
    0.40
    POSITIVE LOGITS
    fprintf
    0.44
    Greg
    0.44
     worsen
    0.44
     پھیل
    0.43
    AEA
    0.43
     worsened
    0.43
     worsening
    0.43
    мая
    0.42
     Worse
    0.42
    拃
    0.42
    Activations Density 0.005%

    No Known Activations