© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205213
    Prev
    Next
    INDEX
    Explanations

    code or functions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Parole
    0.44
    ssä
    0.40
     μεγάλη
    0.38
     wai
    0.36
     klaar
    0.36
    杫
    0.36
    <0xAE>
    0.35
    宠
    0.35
    俠
    0.35
    掰
    0.35
    POSITIVE LOGITS
    Functions
    0.45
    Methods
    0.40
    Means
    0.40
    })$
    0.40
    amino
    0.40
     முற
    0.39
    aux
    0.37
    )}=\
    0.36
    Palette
    0.36
    *}$
    0.36
    Activations Density 0.001%

    No Known Activations