INDEX

Explanations

the prefix "pro-"

oai_token-act-pair · gemini-2.0-flash

pro

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

LookAnd

-0.70

oneofs

-0.59

MigrationBuilder

-0.57

########.

-0.57

cupa

-0.54

assertNotNull

-0.54

 Galbraith

-0.52

 pietre

-0.51

ográficos

-0.51

NewUrlParser

-0.49

POSITIVE LOGITS

 الحره

0.57

posedge

0.56

]));

0.52

setVerticalGroup

0.47

 createContext

0.45

 '\\;'

0.45

 napi

0.44

Beloved

0.43

tops

0.42

ANTLR

0.42

Activations Density 0.330%

the prefix "pro-"

pro

No Comments

No Known Activations