© 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. 180967
    Prev
    Next
    INDEX
    Explanations

    starts of sentences

    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
     එ
    0.51
     Acta
    0.45
     आईएएस
    0.44
    რძ
    0.42
     chr
    0.41
    rosso
    0.41
     ery
    0.41
     Cz
    0.40
     szület
    0.40
    nections
    0.40
    POSITIVE LOGITS
    ਦ
    0.44
    caused
    0.44
    causing
    0.42
    anks
    0.41
     بواسط
    0.41
    sprites
    0.40
    پلز
    0.40
     muqueuse
    0.40
     éché
    0.40
     காவல
    0.39
    Activations Density 0.000%

    No Known Activations