© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5568
    Prev
    Next
    INDEX
    Explanations

    TV shows with the word "the" and mentions of gay or transgender topics.

    oai_token-act-pair · gemini-2.0-flash

    references to TV shows and roles in media

    np_token-act-pair-logits · gpt-4o-mini

    Television shows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    tagHelperRunner
    -0.56
    Erreferentziak
    -0.51
    Gön
    -0.48
    نگار
    -0.46
    OutputType
    -0.46
     <<<<<<<<<<<<<<
    -0.45
     procra
    -0.45
    kozó
    -0.44
    ktı
    -0.44
     interview
    -0.44
    POSITIVE LOGITS
     Allociné
    0.72
    ésia
    0.58
    ViewFeatures
    0.56
    KURZBESCHREIBUNG
    0.54
     חיצוניים
    0.52
    ècie
    0.51
     مرئيه
    0.50
     ProtoMessage
    0.50
     network
    0.50
    findpost
    0.49
    Activations Density 2.311%

    No Known Activations