© 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. 14660
    Prev
    Next
    INDEX
    Explanations

    a variety of different kinds of words that sometimes include numbers, initials, some names/nicknames and some verbs

    oai_token-act-pair · gemini-2.0-flash

    Two letter permutations

    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
    principalTable
    -0.68
     McCullough
    -0.50
     Hackett
    -0.49
     Bengt
    -0.49
    出版年
    -0.47
     Neustadt
    -0.47
     متعلقه
    -0.47
    悅
    -0.47
     Schulz
    -0.47
     Konrad
    -0.45
    POSITIVE LOGITS
     FM
    1.04
     Pm
    1.03
     RM
    1.01
     PM
    1.00
     DM
    1.00
     Fm
    0.98
     pm
    0.97
    Pm
    0.96
     CM
    0.95
     dm
    0.95
    Activations Density 23.840%

    No Known Activations