© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 6007
    Prev
    Next
    INDEX
    Explanations

    azure command terms, especially related to access and deprecation.

    oai_token-act-pair · gemini-2.0-flash

    say "= word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     الحره
    -1.05
    Билгалдахарш
    -1.03
    rungsseite
    -1.02
     saites
    -0.97
    ^(@)
    -0.96
    RenderAtEndOf
    -0.95
    Tikang
    -0.94
    "]:
    -0.93
    ChildScrollView
    -0.93
     doubtnut
    -0.93
    POSITIVE LOGITS
    =
    0.53
    ,
    0.49
    :
    0.42
    )
    0.42
    _
    0.41
    ='
    0.40
     =
    0.40
    ="
    0.39
    -
    0.39
    ;
    0.39
    Activations Density 12.240%

    No Known Activations