INDEX

Explanations

a complex combination of conjunctions, common words, punctuation tokens, and digits

oai_token-act-pair · gemini-2.0-flash

art or media reviews

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

basicConfig

-0.54

총

-0.47

UnsafeEnabled

-0.44

enment

-0.44

oneofs

-0.42

 OGSÅ

-0.41

 résine

-0.40

vatar

-0.40

yce

-0.40

 cold

-0.39

POSITIVE LOGITS

 estekak

0.70

0.69

“

0.64

fjspx

0.62

 jScrollPane

0.61

Abitanti

0.60

้อย

0.60

0.59

‘

0.58

weep

0.56

Activations Density 4.135%

a complex combination of conjunctions, common words, punctuation tokens, and digits

art or media reviews

No Comments

No Known Activations

a complex combination of conjunctions, common words, punctuation tokens, and digits

art or media reviews

No Comments

No Known Activations