INDEX

Explanations

code snippets that perform database operations

oai_token-act-pair · 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

 propOrder

-0.64

Mr

-0.61

Mr

-0.59

 Первый

-0.58

 initComponents

-0.56

Новый

-0.53

Первый

-0.53

Этот

-0.51

 Dieser

-0.51

ptus

-0.50

POSITIVE LOGITS

 للاسماء

0.81

featureID

0.79

ArrowToggle

0.75

IndentedString

0.69

she

0.68

DoubleQuotes

0.64

 beginnetje

0.64

OGND

0.63

 referenties

0.63

skiej

0.61

Activations Density 0.150%

code snippets that perform database operations

No Comments

No Known Activations