INDEX

Explanations

source code with numerical values assigned to particular names

oai_token-act-pair · gemini-2.0-flash

say "='"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

"){

-0.93

"];

-0.91

"){

-0.89

"])

-0.89

":

-0.88

")

-0.88

MigrationBuilder

-0.88

"]];

-0.87

--]

-0.86

migrationBuilder

-0.86

POSITIVE LOGITS

之

0.45

WithIOException

0.45

 Bench

0.44

withCredentials

0.40

方

0.39

 Unsc

0.39

 useHistory

0.39

 sort

0.38

gi

0.37

満

0.37

Activations Density 5.813%

source code with numerical values assigned to particular names

say "='"

No Comments

No Known Activations