© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11508
    Prev
    Next
    INDEX
    Explanations

    job titles or roles associated with or employed by an organization

    oai_token-act-pair · gemini-2.0-flash

    of

    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
    SuppressLint
    -0.55
    ponses
    -0.53
    NoSuchAlgorithm
    -0.52
     autorytatywna
    -0.48
     &
    -0.47
     bcrypt
    -0.47
    DATABASES
    -0.47
     Consultado
    -0.46
    pre
    -0.45
    ப்ப
    -0.45
    POSITIVE LOGITS
    CopyWith
    0.73
    ReusableCell
    0.71
    Kariera
    0.71
    #+#
    0.60
    новништво
    0.56
     Administrativna
    0.56
    aternary
    0.55
     ProtoMessage
    0.55
     AppCompat
    0.54
    ativement
    0.54
    Activations Density 0.882%

    No Known Activations