© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13451
    Prev
    Next
    INDEX
    Explanations

    code snippets referencing the "ToString" function, potentially flagging data type conversions to strings

    oai_token-act-pair · gemini-2.0-flash

    ToString

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    n
    -0.66
    ler
    -0.66
    men
    -0.64
    yt
    -0.60
    now
    -0.59
    ly
    -0.59
    at
    -0.59
    for
    -0.58
    j
    -0.57
    tan
    -0.56
    POSITIVE LOGITS
    protoimpl
    0.94
    tvguidetime
    0.92
    bibfield
    0.88
    bibinfo
    0.86
     Wicidata
    0.86
    :]:
    0.85
    NUMX
    0.85
     Theſe
    0.84
    })*/
    0.82
    olesale
    0.82
    Activations Density 1.501%

    No Known Activations