© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253938
    Prev
    Next
    INDEX
    Explanations

    attackers and attacks

    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
     Process
    0.59
    Process
    0.54
     process
    0.52
     Prozess
    0.49
     Ease
    0.48
     PROCESS
    0.48
    process
    0.46
     都
    0.44
    PROCESS
    0.44
     проце
    0.44
    POSITIVE LOGITS
     realization
    0.57
     use
    0.55
     realized
    0.53
     level
    0.51
    Use
    0.50
     Use
    0.49
    use
    0.48
    level
    0.48
     realize
    0.47
     realizations
    0.47
    Activations Density 0.005%

    No Known Activations