© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261987
    Prev
    Next
    INDEX
    Explanations

    making up facts

    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_22_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
     Cent
    0.40
    Та
    0.39
    Чу
    0.38
     amore
    0.38
    Cent
    0.38
    Metallic
    0.37
    Tick
    0.37
    <0x15>
    0.36
     Recreation
    0.36
     AC
    0.36
    POSITIVE LOGITS
    ilk
    0.44
    termination
    0.42
    when
    0.42
    रांत
    0.42
    beni
    0.41
    琏
    0.41
    quando
    0.41
    inqui
    0.40
    boundaries
    0.40
    auern
    0.40
    Activations Density 0.013%

    No Known Activations