INDEX

Explanations

code snippets including html and json

oai_token-act-pair · gemini-2.0-flash

code, documentation writing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Vikipedi

-0.52

']?>

-0.52

Begriffsklä

-0.49

 reverse

-0.48

"]}

-0.47

]='\

-0.47

 Unsc

-0.46

usermodel

-0.45

 ddelweddau

-0.45

nival

-0.44

POSITIVE LOGITS

PreAuthorize

0.62



0.61

StoryboardSegue

0.60

Kaynakça

0.60

ArgsConstructor

0.57

 مرئيه

0.56

сылкі

0.55

 nakalista

0.55

 disambiguazione

0.52

UserScript

0.52

Activations Density 0.020%

code snippets including html and json

code, documentation writing

No Comments

No Known Activations