INDEX

Explanations

words associated with software applications and their features

oai_token-act-pair · gemini-2.0-flash

technology and software

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

^(@)

-0.77

 ſmall

-0.77

 Theſe

-0.76

 purpoſe

-0.71

 ſtate

-0.66

neſs

-0.66

 fhort

-0.66

wiſe

-0.65

 perſon

-0.65

 fevere

-0.64

POSITIVE LOGITS

in

0.51

 with

0.51

;#

0.49

0.48

UniformLocation

0.47

참고

0.47

be

0.47

—

0.46

を追

0.46

CppMethod

0.46

Activations Density 10.946%

words associated with software applications and their features

technology and software

No Comments

No Known Activations