© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180573
    Prev
    Next
    INDEX
    Explanations

    **circular / central / sound / paragraph / frontal boundaries**

    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_24_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
    Amar
    0.42
    ত্য
    0.42
    ്രി
    0.40
     Soon
    0.39
    cule
    0.39
     oversee
    0.39
    Ridge
    0.39
    ᴡ
    0.38
     oversaw
    0.38
     proclaimed
    0.38
    POSITIVE LOGITS
     soldi
    0.48
    स्कृतिक
    0.45
    abung
    0.44
    των
    0.43
    कह
    0.41
    ﮏ
    0.41
    тол
    0.41
     کہ
    0.40
    irme
    0.40
    tono
    0.40
    Activations Density 0.000%

    No Known Activations