INDEX

Explanations

technical language

np_max-act-logits · gemini-2.0-flash

words related to business, religion, politics, and marketing

oai_token-act-pair · gemini-2.0-flash

Nonsense words or jargon

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ValueStyle

-0.59

✨:

-0.52

Билгалдахарш

-0.51

$:$

-0.50

 Mutation

-0.50

исленность

-0.50

Rohy

-0.48

EndInit

-0.48

 Showers

-0.47

Erreferentziak

-0.47

POSITIVE LOGITS

sizeCache

0.51

fficio

0.51

__((

0.50

sonaro

0.50

ophila

0.48

frei

0.48

enterOuterAlt

0.48

transQ

0.47

Zacks

0.47

twimg

0.46

Activations Density 4.681%

technical language

words related to business, religion, politics, and marketing

Nonsense words or jargon

No Comments

No Known Activations