© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7685
    Prev
    Next
    INDEX
    Explanations

    the letters "CE" capitalized or "fe" in different contexts

    oai_token-act-pair · gemini-2.0-flash

    ce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    getMenuInflater
    -0.63
     onOptions
    -0.61
    ]")]
    -0.59
     []:
    -0.58
     snippetHide
    -0.57
    InstanceState
    -0.57
    AttributeSet
    -0.56
    ConstraintMaker
    -0.56
    illado
    -0.56
    endregion
    -0.56
    POSITIVE LOGITS
    <bos>
    1.05
    '},
    0.66
    ^(@)
    0.59
    amaño
    0.58
    xsi
    0.57
    Referanser
    0.57
     signIn
    0.56
    Климат
    0.56
    '))
    0.56
    izante
    0.55
    Activations Density 1.732%

    No Known Activations