© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10823
    Prev
    Next
    INDEX
    Explanations

    hacking into technology

    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_40_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
    ˦
    0.40
    apeutic
    0.37
     Fog
    0.35
     Cho
    0.35
     покра
    0.35
     Hydro
    0.35
     années
    0.35
     breeding
    0.34
    윳
    0.34
     NTIS
    0.34
    POSITIVE LOGITS
     Tricks
    0.46
    Cheat
    0.45
    Tech
    0.42
    cheat
    0.42
    Trick
    0.42
     TECH
    0.41
     Tech
    0.41
     tricks
    0.40
     Tec
    0.40
     trick
    0.40
    Activations Density 0.030%

    No Known Activations