INDEX

Explanations

java code with the word "Flight" in it

oai_token-act-pair · gemini-2.0-flash

code syntax

np_token-act-pair-logits · gemini-2.0-flash

Less than character

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pote

-0.52

Lock

-0.47

icot

-0.47

lock

-0.46

 lock

-0.46

ka

-0.46

Kas

-0.45

pov

-0.45

ANTLR

-0.45

off

-0.45

POSITIVE LOGITS

 myſelf

0.86

 itſelf

0.78

\{\\

0.77

 AssemblyCompany

0.76

 themſelves

0.74

principalColumn

0.73

 himſelf

0.72

 ſtill

0.69

 Majefty

0.69

 alſo

0.69

Activations Density 1.981%

java code with the word "Flight" in it

code syntax

Less than character

No Comments

No Known Activations