© 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. 24606
    Prev
    Next
    INDEX
    Explanations

    say "app" words

    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
     An
    2.22
    An
    2.13
    安
    1.24
    <0x8E>
    1.21
     AN
    1.14
     안
    1.10
     Ан
    1.10
     anzu
    1.07
     安
    1.04
    an
    0.97
    POSITIVE LOGITS
     claim
    0.61
    用途
    0.59
     appeal
    0.58
     login
    0.58
     Claim
    0.57
     petition
    0.57
     Login
    0.57
    claim
    0.53
    Claim
    0.52
     usage
    0.51
    Activations Density 0.005%

    No Known Activations