© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152702
    Prev
    Next
    INDEX
    Explanations

    brands like Bonds

    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_23_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
     membutuhkan
    0.21
     পরিণত
    0.20
     velik
    0.20
    type
    0.20
    optosis
    0.20
    符
    0.19
     সম্মুখ
    0.18
     doesn
    0.18
     executable
    0.18
     imperme
    0.18
    POSITIVE LOGITS
     Joseph
    0.22
     Caesar
    0.21
     Heritage
    0.20
    ça
    0.20
     circa
    0.20
    ™
    0.20
    Joseph
    0.19
    ARP
    0.19
     Prince
    0.19
     Sars
    0.19
    Activations Density 0.007%

    No Known Activations