© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5712
    Prev
    Next
    INDEX
    Explanations

    durable and lasting

    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_39_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
     Applied
    0.49
    䫒
    0.46
    expired
    0.43
    icidal
    0.42
     programu
    0.40
     muse
    0.39
     departments
    0.38
     Statistical
    0.37
     Casey
    0.37
    副
    0.37
    POSITIVE LOGITS
     waterproof
    0.58
     durable
    0.55
    防水
    0.47
     ens
    0.44
     Waterproof
    0.43
    Metal
    0.43
     Durable
    0.43
    विड़
    0.41
    romb
    0.41
    ⁸
    0.41
    Activations Density 0.005%

    No Known Activations