INDEX

Explanations

text from a Q&A or chat, especially where someone is giving advice

oai_token-act-pair · gemini-2.0-flash

Foreign language context

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

AndEndTag

-1.04

SourceChecksum

-0.71

principalColumn

-0.70

 للمعارف

-0.65

 nahilalakip

-0.65

tagHelperRunner

-0.63

matchCondition

-0.62

keyColumn

-0.61

NameInMap

-0.60

 ModelExpression

-0.60

POSITIVE LOGITS

pag

0.68

Pag

0.64

ang

0.62

sa

0.59

mag

0.59

pag

0.58

Pag

0.55

na

0.49

pa

0.48

Ang

0.48

Activations Density 0.293%

text from a Q&A or chat, especially where someone is giving advice

Foreign language context

No Comments

No Known Activations