© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198045
    Prev
    Next
    INDEX
    Explanations

    pre-con, preconception, preconceived

    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_4_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
    ز
    0.16
    지
    0.16
    3
    0.15
    에
    0.15
    dır
    0.14
    d
    0.14
     affluent
    0.14
    nym
    0.13
    ის
    0.13
    나
    0.13
    POSITIVE LOGITS
    ]
    0.18
    ור
    0.17
    ва
    0.17
    "
    0.17
    то
    0.17
    It
    0.17
     It
    0.16
    ü
    0.16
    )
    0.16
    ile
    0.16
    Activations Density 0.005%

    No Known Activations