© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14656
    Prev
    Next
    INDEX
    Explanations

    text from help forums including thank you's and edit history

    oai_token-act-pair · gemini-2.0-flash

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    igshid
    -0.65
    IRUS
    -0.59
    %;
    -0.59
    _;
    -0.56
     Vikipedi
    -0.54
    ]<<"
    -0.51
     createSlice
    -0.51
    ])):
    -0.51
    --)
    -0.50
     ……………………
    -0.50
    POSITIVE LOGITS
     تضيفلها
    0.76
     Audiodateien
    0.54
     referenties
    0.53
     flori
    0.52
     gloire
    0.51
     also
    0.48
    GraphicsUnit
    0.46
    PyExc
    0.46
     autorytatywna
    0.46
     Puoi
    0.46
    Activations Density 1.465%

    No Known Activations