© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12760
    Prev
    Next
    INDEX
    Explanations

    code related to the MANTIS I2C

    oai_token-act-pair · gemini-2.0-flash

    is

    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
    AddWithValue
    -0.49
    Története
    -0.48
    ecore
    -0.43
    dropdown
    -0.42
    ggi
    -0.42
     aload
    -0.39
    搏
    -0.39
    isen
    -0.38
    为主
    -0.38
    ælde
    -0.38
    POSITIVE LOGITS
     '\\;'
    0.79
    __*/
    0.75
    cknow
    0.70
     newOwner
    0.66
     onCancelled
    0.65
    ISupport
    0.65
    ysław
    0.65
    @[+][
    0.65
    دانشنامهٔ
    0.65
    )».
    0.65
    Activations Density 1.798%

    No Known Activations