© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84232
    Prev
    Next
    INDEX
    Explanations

    this [place/situation]

    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_23_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
     ponownie
    0.28
    again
    0.27
    ăl
    0.27
    el
    0.26
    ra
    0.26
    🧘
    0.26
    ig
    0.25
    ij
    0.25
    how
    0.25
    daction
    0.25
    POSITIVE LOGITS
     accommodates
    0.29
    $),
    0.26
     configure
    0.25
     eliminates
    0.24
     mínimos
    0.24
     けれど
    0.23
     enormes
    0.23
     protested
    0.23
    itemList
    0.23
     fieles
    0.23
    Activations Density 0.004%

    No Known Activations