INDEX

Explanations

content breaks, separators, and parenthetical remarks

oai_token-act-pair · gemini-2.0-flash

research and analysis

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

-0.74

writeFieldEnd

-0.54

opa

-0.52

oas

-0.51

oOo

-0.50

\{\\

-0.49

swire

-0.47

OOOO

-0.47

oc

-0.47

ot

-0.46

POSITIVE LOGITS

că

0.52

ci

0.52

 nakalista

0.52

EndContext

0.52

cak

0.50

ca

0.49

lru

0.48

can

0.48

nya

0.47

ces

0.47

Activations Density 14.143%

content breaks, separators, and parenthetical remarks

research and analysis

No Comments

No Known Activations