INDEX

Explanations

code snippets, especially in swift, pertaining to table views

oai_token-act-pair · gemini-2.0-flash

code

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

TintMode

-0.66

abestanden

-0.63

Jeografia

-0.60

 contemporain

-0.59

🏾

-0.58

 Roskov

-0.57

 contemporaine

-0.56

الحياه

-0.55

közi

-0.54

 varandra

-0.54

POSITIVE LOGITS

UnusedPrivate

0.52

NavController

0.48

if

0.48

uteen

0.46

WarningLevel

0.44

ปิด

0.44

fun

0.44

 secretion

0.43

 postures

0.43

ilians

0.43

Activations Density 0.345%

code snippets, especially in swift, pertaining to table views

code

No Comments

No Known Activations