INDEX

Explanations

words related to computing, electronics, machinery, or manufacturing.

oai_token-act-pair · gemini-2.0-flash

technical descriptions

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

JsonFormat

-0.52

Friendship

-0.49

 coopération

-0.48

 vantaggi

-0.47

 Friendship

-0.47

友情

-0.45

ㅋㅋ

-0.45

 accanto

-0.45

(;;)

-0.44

 cappello

-0.44

POSITIVE LOGITS

 propOrder

0.63

 ©️

0.63

complexContent

0.60

ValueStyle

0.56

getDoctrine

0.56

انجليز

0.55

олові

0.55

 newBuilder

0.54

ffindor

0.54

 برانيه

0.53

Activations Density 1.174%

words related to computing, electronics, machinery, or manufacturing.

technical descriptions

No Comments

No Known Activations