© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8793
    Prev
    Next
    INDEX
    Explanations

    mentions of people being customers or users, and what they can do

    oai_token-act-pair · gemini-2.0-flash

    customers and users

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    sig
    -0.56
    inSlope
    -0.49
    +#+#
    -0.46
    พัน
    -0.45
    sige
    -0.45
    angliski
    -0.45
    VIAF
    -0.44
    cards
    -0.44
    Bains
    -0.44
    Card
    -0.44
    POSITIVE LOGITS
    DoubleQuotes
    0.68
    ंदीखरीदारी
    0.66
     Roskov
    0.64
    IVEREF
    0.60
    iastes
    0.60
    UnitTesting
    0.58
    '])->
    0.56
    MethodManager
    0.56
    IActionResult
    0.51
    vician
    0.51
    Activations Density 0.310%

    No Known Activations