© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14333
    Prev
    Next
    INDEX
    Explanations

    the letter A when it appears as a standalone character or as part of an acronym

    oai_token-act-pair · gemini-2.0-flash

    A

    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
    LookAnd
    -0.78
    RegistryLite
    -0.66
    AA
    -0.64
    AutoScaleMode
    -0.62
    ct
    -0.60
    g
    -0.59
    n
    -0.56
     صوتيه
    -0.54
    bitField
    -0.54
    pp
    -0.54
    POSITIVE LOGITS
    niająca
    0.53
    ungalow
    0.53
    SPATH
    0.50
    wsdl
    0.49
    Comprom
    0.46
    enumii
    0.43
    urnya
    0.43
    viewDidLoad
    0.43
    ukunft
    0.41
    pyplot
    0.40
    Activations Density 0.783%

    No Known Activations