INDEX

Explanations

code-related syntax, including class definitions, data structures, boolean logic, and symbols

oai_token-act-pair · gemini-2.0-flash

colons

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ⓧ

-0.79

 Cæsar

-0.63

 neceſſ

-0.62

 ſeveral

-0.62

 Cicero

-0.62

 poffible

-0.62

 pleaſure

-0.60

 Jefus

-0.58

 itſelf

-0.58

 Tacitus

-0.58

POSITIVE LOGITS

Atsauces

0.52

queryInterface

0.52

 resourceCulture

0.51

cur

0.48

fe

0.47

İstinadlar

0.47

}{@

0.47

 Wave

0.47

 struct

0.46

 INTO

0.45

Activations Density 3.924%

code-related syntax, including class definitions, data structures, boolean logic, and symbols

colons

No Comments

No Known Activations