INDEX

Explanations

months

oai_token-act-pair · gemini-2.0-flash

Months

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

expandindo

-0.85

 kasarigan

-0.84

UserScript

-0.84

bootstrapcdn

-0.83

хьтан

-0.82

IVEREF

-0.81

TypedDataSet

-0.81

 Administrativna

-0.80

 betweenstory

-0.79

 resourceCulture

-0.79

POSITIVE LOGITS

0.72

December

0.45

September

0.43

November

0.42

 December

0.41

posizioni

0.41

March

0.40

 September

0.40

January

0.40

 January

0.40

Activations Density 0.663%

months

Months

No Comments

No Known Activations