INDEX

Explanations

words related to government and technology, as well as numbers

oai_token-act-pair · gemini-2.0-flash

Government documents and code

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

setVerticalGroup

-0.65

NOPQRST

-0.57

ніципа

-0.55

ingly

-0.48

edig

-0.46

 gagné

-0.46

étique

-0.45

bnf

-0.45

 mxArray

-0.44

mitten

-0.43

POSITIVE LOGITS

WriteTagHelper

0.77

enumii

0.71

enumi

0.70

 بيها

0.59

AspNetCore

0.52

Бахар

0.52

mybatisplus

0.51

 parteci

0.49

//});

0.49

lwjgl

0.48

Activations Density 5.361%

words related to government and technology, as well as numbers

Government documents and code

No Comments

No Known Activations