© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169946
    Prev
    Next
    INDEX
    Explanations

    say "forget"

    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
    福
    0.43
     will
    0.40
    will
    0.40
     serve
    0.40
     start
    0.39
    fork
    0.38
     fairly
    0.37
     Not
    0.37
    <unused57>
    0.37
     фор
    0.37
    POSITIVE LOGITS
    Building
    0.50
     recovers
    0.49
     Building
    0.49
     Recovery
    0.48
     building
    0.48
     recovery
    0.47
    Recovery
    0.46
     BUILDING
    0.46
     cabeza
    0.45
    building
    0.45
    Activations Density 0.000%

    No Known Activations