© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 204961
    Prev
    Next
    INDEX
    Explanations

    These are common before a list

    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_25_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
     বাসিন্দ
    0.35
     fu
    0.35
    explored
    0.34
    xo
    0.33
     sépt
    0.33
    窒
    0.33
    尅
    0.33
    俗
    0.32
    }.")
    0.32
     ٹی
    0.31
    POSITIVE LOGITS
     ():
    0.46
    -:
    0.44
    ):
    0.43
     namely
    0.42
    ):
    0.42
     yakni
    0.42
     ]:
    0.42
    *:
    0.41
     iaitu
    0.40
    ’:
    0.40
    Activations Density 0.047%

    No Known Activations