© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6039
    Prev
    Next
    INDEX
    Explanations

    lyrics about self-awareness, shortcomings and love that include the words "we're", "don't", "know", and "love" and are overall negative.

    oai_token-act-pair · gemini-2.0-flash

    Website, Code, or Lyrics

    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
    Rüyada
    -0.60
    mappedBy
    -0.59
     rhestr
    -0.59
     pulumi
    -0.57
     utafiti
    -0.57
    JspWriter
    -0.55
     JUGA
    -0.54
    mtrl
    -0.54
     Cym
    -0.54
    OrBuilder
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.45
    ⋆
    0.42
    Gravity
    0.42
    miary
    0.42
     communicate
    0.42
    ัติ
    0.41
     hide
    0.39
    UNRELATED
    0.39
    polate
    0.38
     criticize
    0.38
    Activations Density 28.240%

    No Known Activations