© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8800
    Prev
    Next
    INDEX
    Explanations

    calls to action, especially those asking the reader to engage or provide feedback

    oai_token-act-pair · gemini-2.0-flash

    Request for action

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ="@+
    -0.76
     CreateTagHelper
    -0.55
     tele
    -0.54
    Shaft
    -0.54
     Ums
    -0.52
    ::$_
    -0.52
    FormState
    -0.51
    flink
    -0.51
    (ﾟ
    -0.50
    rifugal
    -0.50
    POSITIVE LOGITS
     autorytatywna
    0.68
     ProtoMessage
    0.62
     chré
    0.59
     AttributeSet
    0.59
     démocr
    0.57
     réguli
    0.53
     klart
    0.53
     gratuites
    0.52
    Portail
    0.52
     étudi
    0.51
    Activations Density 7.137%

    No Known Activations