© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101897
    Prev
    Next
    INDEX
    Explanations

    conservation efforts and concerns

    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_14_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
    (
    0.61
    io
    0.55
     ]
    0.53
     -
    0.49
     ].
    0.49
                    
    0.48
    java
    0.48
     biologie
    0.47
    ox
    0.47
     biolog
    0.47
    POSITIVE LOGITS
     initially
    0.60
    יל
    0.56
    ORTS
    0.55
     ቢ
    0.53
    Ꮘ
    0.53
     can
    0.52
     ڪري
    0.52
     ጉዳ
    0.52
    どんど
    0.52
     britannique
    0.51
    Activations Density 0.001%

    No Known Activations