INDEX

Explanations

words and phrases related to manual operations or processes.

oai_token-act-pair · gemini-2.0-flash

manual processes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Geplaatst

-0.57

 وتسجيلات

-0.56

 Diſ

-0.55

 tetanus

-0.54

+#+#

-0.53

Хьажоргаш

-0.52

клопе

-0.52

TagHelper

-0.51

`,

-0.50

 potest

-0.49

POSITIVE LOGITS

createStatement

0.67

JSONException

0.62

 aikaa

0.56

createCanvas

0.53

 tradisional

0.52

maries

0.51

ագրություններ

0.51

存于互联网档案馆

0.50

AnchorTagHelper

0.50

\{\\

0.49

Activations Density 1.126%

words and phrases related to manual operations or processes.

manual processes

No Comments

No Known Activations