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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10621
    Prev
    Next
    INDEX
    Explanations

    connections between people and actions, especially attempts or efforts to do something.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    bootstrapcdn
    -0.60
    Geplaatst
    -0.60
    })->
    -0.54
     składa
    -0.54
    ]-->
    -0.52
     ['./
    -0.50
    []):
    -0.50
    oltre
    -0.50
    errar
    -0.50
    pyplot
    -0.49
    POSITIVE LOGITS
    setVerticalGroup
    0.59
     kasarigan
    0.59
    édrale
    0.55
     AttributeSet
    0.54
    évaluateur
    0.52
    FXMLLoader
    0.52
     kaarangay
    0.52
     EClass
    0.52
     sway
    0.50
    تقاوى
    0.50
    Activations Density 3.004%

    No Known Activations