© 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. 14369
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to variable assignment and arithmetic operations

    oai_token-act-pair · gemini-2.0-flash

    code/technical configurations

    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
    IsContent
    -0.70
    tagHelperRunner
    -0.61
    zzleHttp
    -0.53
    criture
    -0.52
    PyExc
    -0.51
     defaultstate
    -0.50
     neceffary
    -0.49
     raiſ
    -0.49
    ]")]
    -0.49
     bens
    -0.47
    POSITIVE LOGITS
    ApiModel
    0.59
    RTEE
    0.56
    antd
    0.55
    مصادر
    0.55
     Autorizaciones
    0.53
    íferos
    0.52
    órico
    0.51
    adaptiveStyles
    0.49
    JsonProperty
    0.49
    writeObject
    0.49
    Activations Density 0.889%

    No Known Activations