© 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. 253734
    Prev
    Next
    INDEX
    Explanations

    tires

    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
     multiplicity
    0.42
     staffed
    0.40
    籍
    0.39
     Staphylococcus
    0.38
    百姓
    0.37
    ја
    0.36
     হৈ
    0.36
    업
    0.36
     CALLBACK
    0.35
    besiege
    0.35
    POSITIVE LOGITS
     rubber
    1.57
     Rubber
    1.41
    Rubber
    1.38
    rubber
    1.34
    橡胶
    1.26
     rubbers
    1.08
    ゴム
    0.96
     caoutchouc
    0.89
    橡
    0.86
     caoutch
    0.80
    Activations Density 0.000%

    No Known Activations