© 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-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5697
    Prev
    Next
    INDEX
    Explanations

    phrases involving "you", "we", or the possibility of something happening

    oai_token-act-pair · gemini-2.0-flash

    Catching

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.84
     Eſ
    -0.76
    ImageContext
    -0.74
     Diſ
    -0.73
     itſelf
    -0.73
     Anſ
    -0.71
     faſt
    -0.70
    RTEX
    -0.70
    ſelf
    -0.69
     ſeveral
    -0.68
    POSITIVE LOGITS
     catch
    0.65
     Catch
    0.65
     caught
    0.59
     catching
    0.59
     us
    0.58
     catches
    0.57
     found
    0.55
     find
    0.54
     encontrarás
    0.53
    catch
    0.52
    Activations Density 0.565%

    No Known Activations