INDEX

Explanations

snippets of medical terminology and codes

oai_token-act-pair · gemini-2.0-flash

technical or code snippets

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

CSR

-0.81

TR

-0.79

cr

-0.79

TSR

-0.79

PSR

-0.79

SR

-0.78

Tr

-0.78

ASR

-0.78

SAR

-0.77

TIR

-0.77

POSITIVE LOGITS

ConstraintMaker

0.56

SharedDtor

0.52

UIControlState

0.51

setViewName

0.48

 SafeMath

0.46

ulink

0.45

 onPostExecute

0.44

 aço

0.43

Билгалдахарш

0.42

 vacuna

0.42

Activations Density 0.937%

snippets of medical terminology and codes

technical or code snippets

No Comments

No Known Activations